From b615bbbff1c4d6fcd13007e75d75f6510aeb3808 Mon Sep 17 00:00:00 2001 From: Mark Salter Date: Wed, 13 Aug 2014 09:04:49 -0700 Subject: [PATCH 01/62] arm: use generic fixmap.h ARM is different from other architectures in that fixmap pages are indexed with a positive offset from FIXADDR_START. Other architectures index with a negative offset from FIXADDR_TOP. In order to use the generic fixmap.h definitions, this patch redefines FIXADDR_TOP to be inclusive of the useable range. That is, FIXADDR_TOP is the virtual address of the topmost fixed page. The newly defined FIXADDR_END is the first virtual address past the fixed mappings. Signed-off-by: Mark Salter Reviewed-by: Doug Anderson [kees: update for a05e54c103b0 ("ARM: 8031/2: change fixmap ...")] Signed-off-by: Kees Cook Cc: Laura Abbott Cc: Rob Herring Acked-by: Nicolas Pitre --- arch/arm/include/asm/fixmap.h | 27 +++++++++------------------ arch/arm/mm/init.c | 2 +- 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index 74124b0d0d79..a7add6f9315d 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -2,27 +2,18 @@ #define _ASM_FIXMAP_H #define FIXADDR_START 0xffc00000UL -#define FIXADDR_TOP 0xffe00000UL -#define FIXADDR_SIZE (FIXADDR_TOP - FIXADDR_START) +#define FIXADDR_END 0xffe00000UL +#define FIXADDR_TOP (FIXADDR_END - PAGE_SIZE) -#define FIX_KMAP_NR_PTES (FIXADDR_SIZE >> PAGE_SHIFT) +#include -#define __fix_to_virt(x) (FIXADDR_START + ((x) << PAGE_SHIFT)) -#define __virt_to_fix(x) (((x) - FIXADDR_START) >> PAGE_SHIFT) +enum fixed_addresses { + FIX_KMAP_BEGIN, + FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1, -extern void __this_fixmap_does_not_exist(void); + __end_of_fixed_addresses +}; -static inline unsigned long fix_to_virt(const unsigned int idx) -{ - if (idx >= FIX_KMAP_NR_PTES) - __this_fixmap_does_not_exist(); - return __fix_to_virt(idx); -} - -static inline unsigned int virt_to_fix(const unsigned long vaddr) -{ - BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); - return __virt_to_fix(vaddr); -} +#include #endif diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 659c75d808dc..ad82c05bfc3a 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -570,7 +570,7 @@ void __init mem_init(void) MLK(DTCM_OFFSET, (unsigned long) dtcm_end), MLK(ITCM_OFFSET, (unsigned long) itcm_end), #endif - MLK(FIXADDR_START, FIXADDR_TOP), + MLK(FIXADDR_START, FIXADDR_END), MLM(VMALLOC_START, VMALLOC_END), MLM(PAGE_OFFSET, (unsigned long)high_memory), #ifdef CONFIG_HIGHMEM From 836a24183273e9db1c092246bd8e306b297d9917 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 2 Jul 2014 02:01:15 -0500 Subject: [PATCH 02/62] ARM: expand fixmap region to 3MB With commit a05e54c103b0 ("ARM: 8031/2: change fixmap mapping region to support 32 CPUs"), the fixmap region was expanded to 2MB, but it precluded any other uses of the fixmap region. In order to support other uses the fixmap region needs to be expanded beyond 2MB. Fortunately, the adjacent 1MB range 0xffe00000-0xfff00000 is availabe. Remove fixmap_page_table ptr and lookup the page table via the virtual address so that the fixmap region can span more that one pmd. The 2nd pmd is already created since it is shared with the vector page. Signed-off-by: Rob Herring [kees: fixed CONFIG_DEBUG_HIGHMEM get_fixmap() calls] [kees: moved pte allocation outside of CONFIG_HIGHMEM] Signed-off-by: Kees Cook Acked-by: Nicolas Pitre --- Documentation/arm/memory.txt | 2 +- arch/arm/include/asm/fixmap.h | 2 +- arch/arm/mm/highmem.c | 15 ++++++++------- arch/arm/mm/mmu.c | 6 +++--- 4 files changed, 13 insertions(+), 12 deletions(-) diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt index 38dc06d0a791..4178ebda6e66 100644 --- a/Documentation/arm/memory.txt +++ b/Documentation/arm/memory.txt @@ -41,7 +41,7 @@ fffe8000 fffeffff DTCM mapping area for platforms with fffe0000 fffe7fff ITCM mapping area for platforms with ITCM mounted inside the CPU. -ffc00000 ffdfffff Fixmap mapping region. Addresses provided +ffc00000 ffefffff Fixmap mapping region. Addresses provided by fix_to_virt() will be located here. fee00000 feffffff Mapping of PCI I/O space. This is a static diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index a7add6f9315d..d984ca69ce19 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -2,7 +2,7 @@ #define _ASM_FIXMAP_H #define FIXADDR_START 0xffc00000UL -#define FIXADDR_END 0xffe00000UL +#define FIXADDR_END 0xfff00000UL #define FIXADDR_TOP (FIXADDR_END - PAGE_SIZE) #include diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 45aeaaca9052..81061987ac45 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -18,19 +18,20 @@ #include #include "mm.h" -pte_t *fixmap_page_table; - static inline void set_fixmap_pte(int idx, pte_t pte) { unsigned long vaddr = __fix_to_virt(idx); - set_pte_ext(fixmap_page_table + idx, pte, 0); + pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr); + + set_pte_ext(ptep, pte, 0); local_flush_tlb_kernel_page(vaddr); } static inline pte_t get_fixmap_pte(unsigned long vaddr) { - unsigned long idx = __virt_to_fix(vaddr); - return *(fixmap_page_table + idx); + pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr); + + return *ptep; } void *kmap(struct page *page) @@ -84,7 +85,7 @@ void *kmap_atomic(struct page *page) * With debugging enabled, kunmap_atomic forces that entry to 0. * Make sure it was indeed properly unmapped. */ - BUG_ON(!pte_none(*(fixmap_page_table + idx))); + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); #endif /* * When debugging is off, kunmap_atomic leaves the previous mapping @@ -134,7 +135,7 @@ void *kmap_atomic_pfn(unsigned long pfn) idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(*(fixmap_page_table + idx))); + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); #endif set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 8348ed6b2efe..7fa0966cd15f 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1326,10 +1326,10 @@ static void __init kmap_init(void) #ifdef CONFIG_HIGHMEM pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE), PKMAP_BASE, _PAGE_KERNEL_TABLE); - - fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START), - FIXADDR_START, _PAGE_KERNEL_TABLE); #endif + + early_pte_alloc(pmd_off_k(FIXADDR_START), FIXADDR_START, + _PAGE_KERNEL_TABLE); } static void __init map_lowmem(void) From 99b4ac9afce4129323b5b4c7002a942a9489914c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 4 Apr 2014 23:27:49 +0200 Subject: [PATCH 03/62] arm: fixmap: implement __set_fixmap() This is used from set_fixmap() and clear_fixmap() via asm-generic/fixmap.h. Also makes sure that the fixmap allocation fits into the expected range. Based on patch by Rabin Vincent. Signed-off-by: Kees Cook Cc: Rabin Vincent Acked-by: Nicolas Pitre --- arch/arm/include/asm/fixmap.h | 2 ++ arch/arm/mm/mmu.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index d984ca69ce19..714606f70425 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -14,6 +14,8 @@ enum fixed_addresses { __end_of_fixed_addresses }; +void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot); + #include #endif diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 7fa0966cd15f..bdf5c94f7c36 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -392,6 +393,29 @@ SET_MEMORY_FN(rw, pte_set_rw) SET_MEMORY_FN(x, pte_set_x) SET_MEMORY_FN(nx, pte_set_nx) +/* + * To avoid TLB flush broadcasts, this uses local_flush_tlb_kernel_range(). + * As a result, this can only be called with preemption disabled, as under + * stop_machine(). + */ +void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) +{ + unsigned long vaddr = __fix_to_virt(idx); + pte_t *pte = pte_offset_kernel(pmd_off_k(vaddr), vaddr); + + /* Make sure fixmap region does not exceed available allocation. */ + BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) > + FIXADDR_END); + BUG_ON(idx >= __end_of_fixed_addresses); + + if (pgprot_val(prot)) + set_pte_at(NULL, vaddr, pte, + pfn_pte(phys >> PAGE_SHIFT, prot)); + else + pte_clear(NULL, vaddr, pte); + local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); +} + /* * Adjust the PMD section entries according to the CPU in use. */ From ab0615e2d6fb074764a3e4d05f1326fa2fdb4627 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 24 Apr 2014 23:28:57 +0200 Subject: [PATCH 04/62] arm: use fixmap for text patching when text is RO Use fixmaps for text patching when the kernel text is read-only, inspired by x86. This makes jump labels and kprobes work with the currently available CONFIG_DEBUG_SET_MODULE_RONX and the upcoming CONFIG_DEBUG_RODATA options. Signed-off-by: Rabin Vincent [kees: fixed up for merge with "arm: use generic fixmap.h"] [kees: added parse acquire/release annotations to pass C=1 builds] [kees: always use stop_machine to keep TLB flushing local] Signed-off-by: Kees Cook Acked-by: Nicolas Pitre --- arch/arm/include/asm/fixmap.h | 4 ++ arch/arm/kernel/jump_label.c | 2 +- arch/arm/kernel/patch.c | 92 +++++++++++++++++++++++++++-------- arch/arm/kernel/patch.h | 12 ++++- 4 files changed, 89 insertions(+), 21 deletions(-) diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index 714606f70425..0415eae1df27 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -11,6 +11,10 @@ enum fixed_addresses { FIX_KMAP_BEGIN, FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1, + /* Support writing RO kernel text via kprobes, jump labels, etc. */ + FIX_TEXT_POKE0, + FIX_TEXT_POKE1, + __end_of_fixed_addresses }; diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c index 4ce4f789446d..afeeb9ea6f43 100644 --- a/arch/arm/kernel/jump_label.c +++ b/arch/arm/kernel/jump_label.c @@ -19,7 +19,7 @@ static void __arch_jump_label_transform(struct jump_entry *entry, insn = arm_gen_nop(); if (is_static) - __patch_text(addr, insn); + __patch_text_early(addr, insn); else patch_text(addr, insn); } diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index 07314af47733..5038960e3c55 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -1,8 +1,11 @@ #include +#include #include +#include #include #include +#include #include #include @@ -13,21 +16,77 @@ struct patch { unsigned int insn; }; -void __kprobes __patch_text(void *addr, unsigned int insn) +static DEFINE_SPINLOCK(patch_lock); + +static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) + __acquires(&patch_lock) +{ + unsigned int uintaddr = (uintptr_t) addr; + bool module = !core_kernel_text(uintaddr); + struct page *page; + + if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX)) + page = vmalloc_to_page(addr); + else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA)) + page = virt_to_page(addr); + else + return addr; + + if (flags) + spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); + + set_fixmap(fixmap, page_to_phys(page)); + + return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); +} + +static void __kprobes patch_unmap(int fixmap, unsigned long *flags) + __releases(&patch_lock) +{ + clear_fixmap(fixmap); + + if (flags) + spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); +} + +void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) { bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL); + unsigned int uintaddr = (uintptr_t) addr; + bool twopage = false; + unsigned long flags; + void *waddr = addr; int size; + if (remap) + waddr = patch_map(addr, FIX_TEXT_POKE0, &flags); + else + __acquire(&patch_lock); + if (thumb2 && __opcode_is_thumb16(insn)) { - *(u16 *)addr = __opcode_to_mem_thumb16(insn); + *(u16 *)waddr = __opcode_to_mem_thumb16(insn); size = sizeof(u16); - } else if (thumb2 && ((uintptr_t)addr & 2)) { + } else if (thumb2 && (uintaddr & 2)) { u16 first = __opcode_thumb32_first(insn); u16 second = __opcode_thumb32_second(insn); - u16 *addrh = addr; + u16 *addrh0 = waddr; + u16 *addrh1 = waddr + 2; - addrh[0] = __opcode_to_mem_thumb16(first); - addrh[1] = __opcode_to_mem_thumb16(second); + twopage = (uintaddr & ~PAGE_MASK) == PAGE_SIZE - 2; + if (twopage && remap) + addrh1 = patch_map(addr + 2, FIX_TEXT_POKE1, NULL); + + *addrh0 = __opcode_to_mem_thumb16(first); + *addrh1 = __opcode_to_mem_thumb16(second); + + if (twopage && addrh1 != addr + 2) { + flush_kernel_vmap_range(addrh1, 2); + patch_unmap(FIX_TEXT_POKE1, NULL); + } size = sizeof(u32); } else { @@ -36,10 +95,16 @@ void __kprobes __patch_text(void *addr, unsigned int insn) else insn = __opcode_to_mem_arm(insn); - *(u32 *)addr = insn; + *(u32 *)waddr = insn; size = sizeof(u32); } + if (waddr != addr) { + flush_kernel_vmap_range(waddr, twopage ? size / 2 : size); + patch_unmap(FIX_TEXT_POKE0, &flags); + } else + __release(&patch_lock); + flush_icache_range((uintptr_t)(addr), (uintptr_t)(addr) + size); } @@ -60,16 +125,5 @@ void __kprobes patch_text(void *addr, unsigned int insn) .insn = insn, }; - if (cache_ops_need_broadcast()) { - stop_machine(patch_text_stop_machine, &patch, cpu_online_mask); - } else { - bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL) - && __opcode_is_thumb32(insn) - && ((uintptr_t)addr & 2); - - if (straddles_word) - stop_machine(patch_text_stop_machine, &patch, NULL); - else - __patch_text(addr, insn); - } + stop_machine(patch_text_stop_machine, &patch, NULL); } diff --git a/arch/arm/kernel/patch.h b/arch/arm/kernel/patch.h index b4731f2dac38..77e054c2f6cd 100644 --- a/arch/arm/kernel/patch.h +++ b/arch/arm/kernel/patch.h @@ -2,6 +2,16 @@ #define _ARM_KERNEL_PATCH_H void patch_text(void *addr, unsigned int insn); -void __patch_text(void *addr, unsigned int insn); +void __patch_text_real(void *addr, unsigned int insn, bool remap); + +static inline void __patch_text(void *addr, unsigned int insn) +{ + __patch_text_real(addr, insn, true); +} + +static inline void __patch_text_early(void *addr, unsigned int insn) +{ + __patch_text_real(addr, insn, false); +} #endif From 42d720d1731a9d7035c2812437c35e271ec4dd78 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 12 May 2014 10:31:56 +0100 Subject: [PATCH 05/62] ARM: kexec: Make .text R/W in machine_kexec With the introduction of Kees Cook's patch to make the kernel .text read-only the existing method by which kexec works got broken since it directly pokes some values in the template code, which resides in the .text section. The current patch changes the way those values are inserted so that poking .text section occurs only in machine_kexec (e.g when we are about to nuke the old kernel and are beyond the point of return). This allows to use set_kernel_text_rw() to directly patch the values in the .text section. I had already sent a patch which achieved this but it was significantly more complicated, so this is a cleaner/straight-forward approach. Signed-off-by: Nikolay Borisov Acked-by: Will Deacon [kees: collapsed kexec_boot_atags (will.daecon)] [kees: for bisectability, moved set_kernel_text_rw() to RODATA patch] Signed-off-by: Kees Cook Acked-by: Nicolas Pitre --- arch/arm/kernel/machine_kexec.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 8cf0996aa1a8..8f75250cbe30 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -29,6 +29,7 @@ extern unsigned long kexec_boot_atags; static atomic_t waiting_for_crash_ipi; +static unsigned long dt_mem; /* * Provide a dummy crash_notes definition while crash dump arrives to arm. * This prevents breakage of crash_notes attribute in kernel/ksysfs.c. @@ -64,7 +65,7 @@ int machine_kexec_prepare(struct kimage *image) return err; if (be32_to_cpu(header) == OF_DT_HEADER) - kexec_boot_atags = current_segment->mem; + dt_mem = current_segment->mem; } return 0; } @@ -166,9 +167,8 @@ void machine_kexec(struct kimage *image) kexec_start_address = image->start; kexec_indirection_page = page_list; kexec_mach_type = machine_arch_type; - if (!kexec_boot_atags) - kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; - + kexec_boot_atags = dt_mem ?: image->start - KEXEC_ARM_ZIMAGE_OFFSET + + KEXEC_ARM_ATAGS_OFFSET; /* copy our kernel relocation code to the control code page */ reboot_entry = fncpy(reboot_code_buffer, From 23a4e4050ba9c98ab67db0980a9fb20e5096d9ea Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Tue, 22 Apr 2014 15:14:51 -0700 Subject: [PATCH 06/62] arm: kgdb: Handle read-only text / modules Handle the case where someone has set the text segment of the kernel as read-only by using the newly introduced "patch" mechanism. Signed-off-by: Doug Anderson [kees: switched structure size check to BUILD_BUG_ON (sboyd)] Signed-off-by: Kees Cook Acked-by: Nicolas Pitre --- arch/arm/kernel/Makefile | 2 +- arch/arm/kernel/kgdb.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 38ddd9f83d0e..70b730766330 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -67,7 +67,7 @@ test-kprobes-objs += kprobes-test-arm.o endif obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o obj-$(CONFIG_ARM_THUMBEE) += thumbee.o -obj-$(CONFIG_KGDB) += kgdb.o +obj-$(CONFIG_KGDB) += kgdb.o patch.o obj-$(CONFIG_ARM_UNWIND) += unwind.o obj-$(CONFIG_HAVE_TCM) += tcm.o obj-$(CONFIG_OF) += devtree.o diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index a74b53c1b7df..07db2f8a1b45 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -12,8 +12,12 @@ #include #include #include +#include + #include +#include "patch.h" + struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { { "r0", 4, offsetof(struct pt_regs, ARM_r0)}, @@ -244,6 +248,31 @@ void kgdb_arch_exit(void) unregister_die_notifier(&kgdb_notifier); } +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + + /* patch_text() only supports int-sized breakpoints */ + BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE); + + err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + BREAK_INSTR_SIZE); + if (err) + return err; + + patch_text((void *)bpt->bpt_addr, + *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr); + + return err; +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ + patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr); + + return 0; +} + /* * Register our undef instruction hooks with ARM undef core. * We regsiter a hook specifically looking for the KGB break inst From 1e6b48116a95046ec51f3d40f83aff8b006674d7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 3 Apr 2014 17:28:11 -0700 Subject: [PATCH 07/62] ARM: mm: allow non-text sections to be non-executable Adds CONFIG_ARM_KERNMEM_PERMS to separate the kernel memory regions into section-sized areas that can have different permisions. Performs the NX permission changes during free_initmem, so that init memory can be reclaimed. This uses section size instead of PMD size to reduce memory lost to padding on non-LPAE systems. Based on work by Brad Spengler, Larry Bassel, and Laura Abbott. Signed-off-by: Kees Cook Tested-by: Laura Abbott Acked-by: Nicolas Pitre --- arch/arm/kernel/vmlinux.lds.S | 16 ++++++ arch/arm/mm/Kconfig | 9 +++ arch/arm/mm/init.c | 101 +++++++++++++++++++++++++++++++++- arch/arm/mm/mmu.c | 9 ++- 4 files changed, 133 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 6f57cb94367f..18fd68a295ea 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -8,6 +8,9 @@ #include #include #include +#ifdef CONFIG_ARM_KERNMEM_PERMS +#include +#endif #define PROC_INFO \ . = ALIGN(4); \ @@ -90,6 +93,11 @@ SECTIONS _text = .; HEAD_TEXT } + +#ifdef CONFIG_ARM_KERNMEM_PERMS + . = ALIGN(1< #include #include +#include #include #include @@ -615,7 +616,99 @@ void __init mem_init(void) } } -void free_initmem(void) +#ifdef CONFIG_ARM_KERNMEM_PERMS +struct section_perm { + unsigned long start; + unsigned long end; + pmdval_t mask; + pmdval_t prot; +}; + +struct section_perm nx_perms[] = { + /* Make pages tables, etc before _stext RW (set NX). */ + { + .start = PAGE_OFFSET, + .end = (unsigned long)_stext, + .mask = ~PMD_SECT_XN, + .prot = PMD_SECT_XN, + }, + /* Make init RW (set NX). */ + { + .start = (unsigned long)__init_begin, + .end = (unsigned long)_sdata, + .mask = ~PMD_SECT_XN, + .prot = PMD_SECT_XN, + }, +}; + +/* + * Updates section permissions only for the current mm (sections are + * copied into each mm). During startup, this is the init_mm. Is only + * safe to be called with preemption disabled, as under stop_machine(). + */ +static inline void section_update(unsigned long addr, pmdval_t mask, + pmdval_t prot) +{ + struct mm_struct *mm; + pmd_t *pmd; + + mm = current->active_mm; + pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr); + +#ifdef CONFIG_ARM_LPAE + pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot); +#else + if (addr & SECTION_SIZE) + pmd[1] = __pmd((pmd_val(pmd[1]) & mask) | prot); + else + pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot); +#endif + flush_pmd_entry(pmd); + local_flush_tlb_kernel_range(addr, addr + SECTION_SIZE); +} + +/* Make sure extended page tables are in use. */ +static inline bool arch_has_strict_perms(void) +{ + if (cpu_architecture() < CPU_ARCH_ARMv6) + return false; + + return !!(get_cr() & CR_XP); +} + +#define set_section_perms(perms, field) { \ + size_t i; \ + unsigned long addr; \ + \ + if (!arch_has_strict_perms()) \ + return; \ + \ + for (i = 0; i < ARRAY_SIZE(perms); i++) { \ + if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || \ + !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { \ + pr_err("BUG: section %lx-%lx not aligned to %lx\n", \ + perms[i].start, perms[i].end, \ + SECTION_SIZE); \ + continue; \ + } \ + \ + for (addr = perms[i].start; \ + addr < perms[i].end; \ + addr += SECTION_SIZE) \ + section_update(addr, perms[i].mask, \ + perms[i].field); \ + } \ +} + +static inline void fix_kernmem_perms(void) +{ + set_section_perms(nx_perms, prot); +} +#else +static inline void fix_kernmem_perms(void) { } +#endif /* CONFIG_ARM_KERNMEM_PERMS */ + +void free_tcmmem(void) { #ifdef CONFIG_HAVE_TCM extern char __tcm_start, __tcm_end; @@ -623,6 +716,12 @@ void free_initmem(void) poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start); free_reserved_area(&__tcm_start, &__tcm_end, -1, "TCM link"); #endif +} + +void free_initmem(void) +{ + fix_kernmem_perms(); + free_tcmmem(); poison_init_mem(__init_begin, __init_end - __init_begin); if (!machine_is_integrator() && !machine_is_cintegrator()) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index bdf5c94f7c36..1c52c8e94372 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1373,12 +1373,19 @@ static void __init map_lowmem(void) if (start >= end) break; - if (end < kernel_x_start || start >= kernel_x_end) { + if (end < kernel_x_start) { map.pfn = __phys_to_pfn(start); map.virtual = __phys_to_virt(start); map.length = end - start; map.type = MT_MEMORY_RWX; + create_mapping(&map); + } else if (start >= kernel_x_end) { + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_RW; + create_mapping(&map); } else { /* This better cover the entire kernel */ From 80d6b0c2eed2a504f6740cd1f5ea76dc50abfc4d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 3 Apr 2014 13:29:50 -0700 Subject: [PATCH 08/62] ARM: mm: allow text and rodata sections to be read-only This introduces CONFIG_DEBUG_RODATA, making kernel text and rodata read-only. Additionally, this splits rodata from text so that rodata can also be NX, which may lead to wasted memory when aligning to SECTION_SIZE. The read-only areas are made writable during ftrace updates and kexec. Signed-off-by: Kees Cook Tested-by: Laura Abbott Acked-by: Nicolas Pitre --- arch/arm/include/asm/cacheflush.h | 10 +++++++ arch/arm/kernel/ftrace.c | 19 ++++++++++++ arch/arm/kernel/machine_kexec.c | 1 + arch/arm/kernel/vmlinux.lds.S | 3 ++ arch/arm/mm/Kconfig | 12 ++++++++ arch/arm/mm/init.c | 48 ++++++++++++++++++++++++++++++- 6 files changed, 92 insertions(+), 1 deletion(-) diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 10e78d00a0bb..2d46862e7bef 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -487,6 +487,16 @@ int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } +#endif + void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, void *kaddr, unsigned long len); + #endif diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index af9a8a927a4e..b8c75e45a950 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -35,6 +36,22 @@ #define OLD_NOP 0xe1a00000 /* mov r0, r0 */ +static int __ftrace_modify_code(void *data) +{ + int *command = data; + + set_kernel_text_rw(); + ftrace_modify_all_code(*command); + set_kernel_text_ro(); + + return 0; +} + +void arch_ftrace_update_code(int command) +{ + stop_machine(__ftrace_modify_code, &command, NULL); +} + static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec) { return rec->arch.old_mcount ? OLD_NOP : NOP; @@ -73,6 +90,8 @@ int ftrace_arch_code_modify_prepare(void) int ftrace_arch_code_modify_post_process(void) { set_all_modules_text_ro(); + /* Make sure any TLB misses during machine stop are cleared. */ + flush_tlb_all(); return 0; } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 8f75250cbe30..4423a565ef6f 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -164,6 +164,7 @@ void machine_kexec(struct kimage *image) reboot_code_buffer = page_address(image->control_code_page); /* Prepare parameters for reboot_code_buffer*/ + set_kernel_text_rw(); kexec_start_address = image->start; kexec_indirection_page = page_list; kexec_mach_type = machine_arch_type; diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 18fd68a295ea..3afcb6c2cf06 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -120,6 +120,9 @@ SECTIONS ARM_CPU_KEEP(PROC_INFO) } +#ifdef CONFIG_DEBUG_RODATA + . = ALIGN(1< Date: Sat, 27 Sep 2014 00:31:04 +0100 Subject: [PATCH 09/62] ARM: 8170/1: Add global named register current_stack_pointer for ARM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a global named register for current_stack_pointer. The use of this new variable guarantees that both gcc and clang can access this register in C code. Signed-off-by: Behan Webster Reviewed-by: Jan-Simon Möller Reviewed-by: Mark Charlebois Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/include/asm/thread_info.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index fc44d3761f9e..bb435152189f 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -100,6 +100,11 @@ struct thread_info { #define init_thread_info (init_thread_union.thread_info) #define init_stack (init_thread_union.stack) +/* + * how to get the current stack pointer in C + */ +register unsigned long current_stack_pointer asm ("sp"); + /* * how to get the thread information struct from C */ From a556ee1247b99720d9ba6d8a3ed43dd960575d07 Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Sat, 27 Sep 2014 00:31:07 +0100 Subject: [PATCH 10/62] ARM: 8171/1: Use current_stack_pointer for return_address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the global current_stack_pointer to get the value of the stack pointer. This change supports being able to compile the kernel with both gcc and Clang. Signed-off-by: Behan Webster Reviewed-by: Mark Charlebois Reviewed-by: Jan-Simon Möller Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/kernel/return_address.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c index 98ea4b7eb406..24b4a04846eb 100644 --- a/arch/arm/kernel/return_address.c +++ b/arch/arm/kernel/return_address.c @@ -39,13 +39,12 @@ void *return_address(unsigned int level) { struct return_address_data data; struct stackframe frame; - register unsigned long current_sp asm ("sp"); data.level = level + 2; data.addr = NULL; frame.fp = (unsigned long)__builtin_frame_address(0); - frame.sp = current_sp; + frame.sp = current_stack_pointer; frame.lr = (unsigned long)__builtin_return_address(0); frame.pc = (unsigned long)return_address; From 74dbeee0fcded9525ddb42b53ee75dc62c8089d9 Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Sat, 27 Sep 2014 00:31:08 +0100 Subject: [PATCH 11/62] ARM: 8172/1: Use current_stack_pointer in save_stack_trace_tsk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the global current_stack_pointer to get the value of the stack pointer. This change supports being able to compile the kernel with both gcc and clang. Signed-off-by: Behan Webster Reviewed-by: Mark Charlebois Reviewed-by: Jan-Simon Möller Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/kernel/stacktrace.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index f065eb05d254..92b72375c4c7 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -134,12 +134,10 @@ static noinline void __save_stack_trace(struct task_struct *tsk, frame.pc = thread_saved_pc(tsk); #endif } else { - register unsigned long current_sp asm ("sp"); - /* We don't want this function nor the caller */ data.skip += 2; frame.fp = (unsigned long)__builtin_frame_address(0); - frame.sp = current_sp; + frame.sp = current_stack_pointer; frame.lr = (unsigned long)__builtin_return_address(0); frame.pc = (unsigned long)__save_stack_trace; } From f6c9cbf091a4b0769180d663e37621569b054d11 Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Sat, 27 Sep 2014 00:31:09 +0100 Subject: [PATCH 12/62] ARM: 8173/1: Calculate current_thread_info from current_stack_pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the global current_stack_pointer to get the value of the stack pointer. This change supports being able to compile the kernel with both gcc and clang. Signed-off-by: Behan Webster Reviewed-by: Mark Charlebois Reviewed-by: Jan-Simon Möller Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/include/asm/thread_info.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index bb435152189f..b9dc3dce59a6 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -112,8 +112,8 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__; static inline struct thread_info *current_thread_info(void) { - register unsigned long sp asm ("sp"); - return (struct thread_info *)(sp & ~(THREAD_SIZE - 1)); + return (struct thread_info *) + (current_stack_pointer & ~(THREAD_SIZE - 1)); } #define thread_saved_pc(tsk) \ From ccbd2da50db2111f6d055e3201c39a37e542ceb6 Mon Sep 17 00:00:00 2001 From: Mark Charlebois Date: Sat, 27 Sep 2014 00:31:05 +0100 Subject: [PATCH 13/62] ARM: 8174/1: Use global stack register variable for percpu Using global current_stack_pointer works on both clang and gcc. current_stack_pointer is an unsigned long and needs to be cast as a pointer to dereference. Signed-off-by: Mark Charlebois Signed-off-by: Behan Webster Signed-off-by: Russell King --- arch/arm/include/asm/percpu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index 209e6504922e..a89b4076cde4 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -30,14 +30,14 @@ static inline void set_my_cpu_offset(unsigned long off) static inline unsigned long __my_cpu_offset(void) { unsigned long off; - register unsigned long *sp asm ("sp"); /* * Read TPIDRPRW. * We want to allow caching the value, so avoid using volatile and * instead use a fake stack read to hazard against barrier(). */ - asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : "Q" (*sp)); + asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) + : "Q" (*(const unsigned long *)current_stack_pointer)); return off; } From 0ebc1f5671dff84b7ba4dcc38ebce956e6dea5fa Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Sat, 27 Sep 2014 00:31:06 +0100 Subject: [PATCH 14/62] ARM: 8175/1: Use current_stack_pointer to calculate pt_regs address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the global current_stack_pointer to calculate the end of the stack for current_pt_regs() Signed-off-by: Behan Webster Reviewed-by: Mark Charlebois Reviewed-by: Jan-Simon Möller Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/include/asm/ptrace.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index 601264d983fa..51622ba7c4a6 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -154,9 +154,8 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) return regs->ARM_sp; } -#define current_pt_regs(void) ({ \ - register unsigned long sp asm ("sp"); \ - (struct pt_regs *)((sp | (THREAD_SIZE - 1)) - 7) - 1; \ +#define current_pt_regs(void) ({ (struct pt_regs *) \ + ((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1; \ }) #endif /* __ASSEMBLY__ */ From 0bf4954f248c59705470bae2210f67a4b03f8f3c Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Sat, 27 Sep 2014 00:31:10 +0100 Subject: [PATCH 15/62] ARM: 8176/1: Use current_stack_pointer in unwind_backtrace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the global current_stack_pointer to get the value of the stack pointer. This change supports being able to compile the kernel with both gcc and clang. Signed-off-by: Behan Webster Reviewed-by: Mark Charlebois Reviewed-by: Jan-Simon Möller Acked-by: Will Deacon Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/kernel/unwind.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index cbb85c5fabf9..0bee233fef9a 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -471,7 +471,6 @@ int unwind_frame(struct stackframe *frame) void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - register unsigned long current_sp asm ("sp"); pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); @@ -485,7 +484,7 @@ void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.pc = regs->ARM_lr; } else if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); - frame.sp = current_sp; + frame.sp = current_stack_pointer; frame.lr = (unsigned long)__builtin_return_address(0); frame.pc = (unsigned long)unwind_backtrace; } else { From 3fb1581ea1ab0aec6ac5430dc0e257a8c9b71680 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 14 Nov 2014 09:47:25 +0100 Subject: [PATCH 16/62] ARM: 8199/1: PM / Runtime: Add getter for querying the IRQ safe option v12 Add a simple getter pm_runtime_is_irq_safe() for querying whether runtime PM IRQ safe was set or not. Various bus drivers implementing runtime PM may use choose to suspend differently based on IRQ safeness status of child driver (e.g. do not unprepare the clock if IRQ safe is not set). Signed-off-by: Krzysztof Kozlowski Reviewed-by: Ulf Hansson Acked-by: Rafael J. Wysocki Signed-off-by: Russell King --- Documentation/power/runtime_pm.txt | 4 ++++ include/linux/pm_runtime.h | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index f32ce5419573..397b81593142 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -468,6 +468,10 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: - set the power.irq_safe flag for the device, causing the runtime-PM callbacks to be invoked with interrupts off + bool pm_runtime_is_irq_safe(struct device *dev); + - return true if power.irq_safe flag was set for the device, causing + the runtime-PM callbacks to be invoked with interrupts off + void pm_runtime_mark_last_busy(struct device *dev); - set the power.last_busy field to the current time diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 367f49b9a1c9..44d74f0f182e 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -128,6 +128,11 @@ static inline void pm_runtime_mark_last_busy(struct device *dev) ACCESS_ONCE(dev->power.last_busy) = jiffies; } +static inline bool pm_runtime_is_irq_safe(struct device *dev) +{ + return dev->power.irq_safe; +} + #else /* !CONFIG_PM_RUNTIME */ static inline int __pm_runtime_idle(struct device *dev, int rpmflags) @@ -167,6 +172,7 @@ static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} +static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_callbacks_present(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} From f560e3229564a673603541ebfb36118d7cd98038 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 14 Nov 2014 09:47:49 +0100 Subject: [PATCH 17/62] ARM: 8200/1: amba: Add helpers for (un)preparing AMBA clock v12 Add amba_pclk_prepare() and amba_pclk_unprepare() inline functions for handling the AMBA bus clock by device drivers. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Ulf Hansson Signed-off-by: Russell King --- include/linux/amba/bus.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c324f5700d1a..ac02f9bd63dc 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -97,6 +97,16 @@ void amba_release_regions(struct amba_device *); #define amba_pclk_disable(d) \ do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0) +static inline int amba_pclk_prepare(struct amba_device *dev) +{ + return clk_prepare(dev->pclk); +} + +static inline void amba_pclk_unprepare(struct amba_device *dev) +{ + clk_unprepare(dev->pclk); +} + /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) From 5670c2a52f60418f67dd589e20d30600804fcfde Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 14 Nov 2014 09:48:27 +0100 Subject: [PATCH 18/62] ARM: 8201/1: amba: Don't unprepare the clocks if device driver wants IRQ safe runtime PM v12 The AMBA bus driver defines runtime Power Management functions which disable and unprepare AMBA bus clock. This is problematic for runtime PM because unpreparing a clock might sleep so it is not interrupt safe. However some drivers may want to implement runtime PM functions in interrupt-safe way (see pm_runtime_irq_safe()). In such case the AMBA bus driver should only disable/enable the clock in runtime suspend and resume callbacks. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Ulf Hansson Signed-off-by: Russell King --- drivers/amba/bus.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 47bbdc1b5be3..f8e3bb44938e 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -95,8 +95,12 @@ static int amba_pm_runtime_suspend(struct device *dev) struct amba_device *pcdev = to_amba_device(dev); int ret = pm_generic_runtime_suspend(dev); - if (ret == 0 && dev->driver) - clk_disable_unprepare(pcdev->pclk); + if (ret == 0 && dev->driver) { + if (pm_runtime_is_irq_safe(dev)) + clk_disable(pcdev->pclk); + else + clk_disable_unprepare(pcdev->pclk); + } return ret; } @@ -107,7 +111,10 @@ static int amba_pm_runtime_resume(struct device *dev) int ret; if (dev->driver) { - ret = clk_prepare_enable(pcdev->pclk); + if (pm_runtime_is_irq_safe(dev)) + ret = clk_enable(pcdev->pclk); + else + ret = clk_prepare_enable(pcdev->pclk); /* Failure is probably fatal to the system, but... */ if (ret) return ret; @@ -115,7 +122,7 @@ static int amba_pm_runtime_resume(struct device *dev) return pm_generic_runtime_resume(dev); } -#endif +#endif /* CONFIG_PM */ static const struct dev_pm_ops amba_pm = { .suspend = pm_generic_suspend, From ae43b3289186480f81c78bb63d788a85a3631f47 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 14 Nov 2014 09:48:57 +0100 Subject: [PATCH 19/62] ARM: 8202/1: dmaengine: pl330: Add runtime Power Management support v12 This patch adds runtime PM support to pl330 DMA engine driver. The runtime power management for pl330 DMA driver allows gating of AMBA clock (PDMA) in FSYS clock domain, when the device is not processing any requests. This is necessary to enter low power modes on Exynos SoCs (e.g. LPA on Exynos4x12 or W-AFTR on Exynos3250). Runtime PM resuming of the device may happen in atomic context (during call device_issue_pending()) so pm_runtime_irq_safe() is used. This will lead only to disabling/enabling of the clock but this is sufficient for gating the clock and for reducing energy usage. Driver uses runtime PM callbacks from amba/bus.c driver only. Suggested-by: Bartlomiej Zolnierkiewicz Signed-off-by: Krzysztof Kozlowski Reviewed-by: Ulf Hansson Acked-by: Vinod Koul Signed-off-by: Russell King --- drivers/dma/pl330.c | 58 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 54 insertions(+), 4 deletions(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 4839bfa74a10..39ea8d436b81 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "dmaengine.h" #define PL330_MAX_CHAN 8 @@ -265,6 +266,9 @@ static unsigned cmd_line; #define NR_DEFAULT_DESC 16 +/* Delay for runtime PM autosuspend, ms */ +#define PL330_AUTOSUSPEND_DELAY 20 + /* Populated by the PL330 core driver for DMA API driver's info */ struct pl330_config { u32 periph_id; @@ -1958,6 +1962,7 @@ static void pl330_tasklet(unsigned long data) struct dma_pl330_chan *pch = (struct dma_pl330_chan *)data; struct dma_pl330_desc *desc, *_dt; unsigned long flags; + bool power_down = false; spin_lock_irqsave(&pch->lock, flags); @@ -1972,10 +1977,17 @@ static void pl330_tasklet(unsigned long data) /* Try to submit a req imm. next to the last completed cookie */ fill_queue(pch); - /* Make sure the PL330 Channel thread is active */ - spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); - spin_unlock(&pch->thread->dmac->lock); + if (list_empty(&pch->work_list)) { + spin_lock(&pch->thread->dmac->lock); + _stop(pch->thread); + spin_unlock(&pch->thread->dmac->lock); + power_down = true; + } else { + /* Make sure the PL330 Channel thread is active */ + spin_lock(&pch->thread->dmac->lock); + _start(pch->thread); + spin_unlock(&pch->thread->dmac->lock); + } while (!list_empty(&pch->completed_list)) { dma_async_tx_callback callback; @@ -1990,6 +2002,12 @@ static void pl330_tasklet(unsigned long data) if (pch->cyclic) { desc->status = PREP; list_move_tail(&desc->node, &pch->work_list); + if (power_down) { + spin_lock(&pch->thread->dmac->lock); + _start(pch->thread); + spin_unlock(&pch->thread->dmac->lock); + power_down = false; + } } else { desc->status = FREE; list_move_tail(&desc->node, &pch->dmac->desc_pool); @@ -2004,6 +2022,12 @@ static void pl330_tasklet(unsigned long data) } } spin_unlock_irqrestore(&pch->lock, flags); + + /* If work list empty, power down */ + if (power_down) { + pm_runtime_mark_last_busy(pch->dmac->ddma.dev); + pm_runtime_put_autosuspend(pch->dmac->ddma.dev); + } } bool pl330_filter(struct dma_chan *chan, void *param) @@ -2073,6 +2097,7 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned switch (cmd) { case DMA_TERMINATE_ALL: + pm_runtime_get_sync(pl330->ddma.dev); spin_lock_irqsave(&pch->lock, flags); spin_lock(&pl330->lock); @@ -2099,10 +2124,15 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned dma_cookie_complete(&desc->txd); } + if (!list_empty(&pch->work_list)) + pm_runtime_put(pl330->ddma.dev); + list_splice_tail_init(&pch->submitted_list, &pl330->desc_pool); list_splice_tail_init(&pch->work_list, &pl330->desc_pool); list_splice_tail_init(&pch->completed_list, &pl330->desc_pool); spin_unlock_irqrestore(&pch->lock, flags); + pm_runtime_mark_last_busy(pl330->ddma.dev); + pm_runtime_put_autosuspend(pl330->ddma.dev); break; case DMA_SLAVE_CONFIG: slave_config = (struct dma_slave_config *)arg; @@ -2138,6 +2168,7 @@ static void pl330_free_chan_resources(struct dma_chan *chan) tasklet_kill(&pch->task); + pm_runtime_get_sync(pch->dmac->ddma.dev); spin_lock_irqsave(&pch->lock, flags); pl330_release_channel(pch->thread); @@ -2147,6 +2178,8 @@ static void pl330_free_chan_resources(struct dma_chan *chan) list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool); spin_unlock_irqrestore(&pch->lock, flags); + pm_runtime_mark_last_busy(pch->dmac->ddma.dev); + pm_runtime_put_autosuspend(pch->dmac->ddma.dev); } static enum dma_status @@ -2162,6 +2195,15 @@ static void pl330_issue_pending(struct dma_chan *chan) unsigned long flags; spin_lock_irqsave(&pch->lock, flags); + if (list_empty(&pch->work_list)) { + /* + * Warn on nothing pending. Empty submitted_list may + * break our pm_runtime usage counter as it is + * updated on work_list emptiness status. + */ + WARN_ON(list_empty(&pch->submitted_list)); + pm_runtime_get_sync(pch->dmac->ddma.dev); + } list_splice_tail_init(&pch->submitted_list, &pch->work_list); spin_unlock_irqrestore(&pch->lock, flags); @@ -2738,6 +2780,12 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pcfg->data_buf_dep, pcfg->data_bus_width / 8, pcfg->num_chan, pcfg->num_peri, pcfg->num_events); + pm_runtime_irq_safe(&adev->dev); + pm_runtime_use_autosuspend(&adev->dev); + pm_runtime_set_autosuspend_delay(&adev->dev, PL330_AUTOSUSPEND_DELAY); + pm_runtime_mark_last_busy(&adev->dev); + pm_runtime_put_autosuspend(&adev->dev); + return 0; probe_err3: /* Idle the DMAC */ @@ -2764,6 +2812,8 @@ static int pl330_remove(struct amba_device *adev) struct pl330_dmac *pl330 = amba_get_drvdata(adev); struct dma_pl330_chan *pch, *_p; + pm_runtime_get_noresume(pl330->ddma.dev); + if (adev->dev.of_node) of_dma_controller_free(adev->dev.of_node); From 09415fa2c58b61ac766816e914ef5872011b4861 Mon Sep 17 00:00:00 2001 From: Yalin Wang Date: Thu, 6 Nov 2014 03:40:07 +0100 Subject: [PATCH 20/62] ARM: 8194/1: remove clear_thread_flag(TIF_UPROBE) This patch remove clear_thread_flag(TIF_UPROBE) in do_work_pending(), because uprobe_notify_resume() have do this. Signed-off-by: Yalin Wang Signed-off-by: Russell King --- arch/arm/kernel/signal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index bd1983437205..8aa6f1b87c9e 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -592,7 +592,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } syscall = 0; } else if (thread_flags & _TIF_UPROBE) { - clear_thread_flag(TIF_UPROBE); uprobe_notify_resume(regs); } else { clear_thread_flag(TIF_NOTIFY_RESUME); From 1ca8bf6f7ba581d8b47144ff5a558e17fba3190d Mon Sep 17 00:00:00 2001 From: Stepan Moskovchenko Date: Mon, 10 Nov 2014 21:56:42 +0100 Subject: [PATCH 21/62] ARM: 8195/1: vfp: Bounce undefined instructions in vectored mode Certain ARM CPU implementations (e.g. Cortex-A15) may not raise a floating- point exception whenever deprecated short-vector VFP instructions are executed. Instead these instructions are treated as UNALLOCATED. Change the VFP exception handling code to emulate short-vector instructions even if FPEXC exception bits are not set. Signed-off-by: Stepan Moskovchenko Tested-by: Will Deacon Tested-by: Rob Clark Signed-off-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/vfp/vfphw.S | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index cda654cbf2c2..f74a8f7e5f84 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -197,6 +197,12 @@ look_for_VFP_exceptions: tst r5, #FPSCR_IXE bne process_exception + tst r5, #FPSCR_LENGTH_MASK + beq skip + orr r1, r1, #FPEXC_DEX + b process_exception +skip: + @ Fall into hand on to next handler - appropriate coproc instr @ not recognised by VFP From 6f0f2a9f0f8f420f604e1ae06f1d24cc9b61a9d0 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 10 Nov 2014 21:56:40 +0100 Subject: [PATCH 22/62] ARM: 8196/1: vfp: Workaround bad MVFR1 register on some Kraits Certain versions of the Krait processor don't report that they support the fused multiply accumulate instruction via the MVFR1 register despite the fact that they actually do. Unfortunately we use this register to identify support for VFPv4. Override the hwcap on all Krait processors to indicate support for VFPv4 to workaround this. Tested-by: Rob Clark Signed-off-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/mm/proc-v7.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index b3a947863ac7..6c33eaf879ae 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -593,9 +593,10 @@ __krait_proc_info: /* * Some Krait processors don't indicate support for SDIV and UDIV * instructions in the ARM instruction set, even though they actually - * do support them. + * do support them. They also don't indicate support for fused multiply + * instructions even though they actually do support them. */ - __v7_proc __v7_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_setup, hwcaps = HWCAP_IDIV | HWCAP_VFPv4 .size __krait_proc_info, . - __krait_proc_info /* From 6c96a4a6e249a0580b32893583771149e0611375 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 10 Nov 2014 21:56:41 +0100 Subject: [PATCH 23/62] ARM: 8197/1: vfp: Fix VFPv3 hwcap detection on CPUID based cpus The subarchitecture field in the fpsid register is 7 bits wide on ARM CPUs using the CPUID identification scheme, spanning bits 22 to 16. The topmost bit is used to designate that the subarchitecture designer is not ARM when it is set to 1. On non-CPUID scheme CPUs the subarchitecture field is only 4 bits wide and the higher bits are used to indicate no double precision support (bit 20) and the FTSMX/FLDMX format (bits 21-22). The VFP support code only looks at bits 19-16 to determine the VFP version. On Qualcomm's processors (Krait and Scorpion) we should see that we have HWCAP_VFPv3 but we don't because bit 22 is set to 1 to indicate that the subarchitecture is not implemented by ARM and the rest of the bits are left as 0 because this is the first subarchitecture that Qualcomm has designed. Unfortunately we can't just widen the FPSID subarchitecture bitmask to consider all the bits on a CPUID scheme because there may be CPUs without the CPUID scheme that have VFP without double precision support and then the version would be a very wrong and large number. Instead, update the version detection logic to consider if the CPU is using the CPUID scheme. If the CPU is using CPUID scheme, use the MVFR registers to determine what version of VFP is supported. We already do this for VFPv4, so do something similar for VFPv3 and look for single or double precision support in MVFR0. Otherwise fall back to using FPSID to detect VFP support on non-CPUID scheme CPUs. We know that VFPv3 is only present in CPUs that have support for the CPUID scheme so this should be equivalent. Tested-by: Rob Clark Reviewed-by: Will Deacon Signed-off-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/include/asm/vfp.h | 5 ++ arch/arm/vfp/vfpmodule.c | 101 ++++++++++++++++++++----------------- 2 files changed, 61 insertions(+), 45 deletions(-) diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h index f4ab34fd4f72..ee5f3084243c 100644 --- a/arch/arm/include/asm/vfp.h +++ b/arch/arm/include/asm/vfp.h @@ -22,6 +22,7 @@ #define FPSID_NODOUBLE (1<<20) #define FPSID_ARCH_BIT (16) #define FPSID_ARCH_MASK (0xF << FPSID_ARCH_BIT) +#define FPSID_CPUID_ARCH_MASK (0x7F << FPSID_ARCH_BIT) #define FPSID_PART_BIT (8) #define FPSID_PART_MASK (0xFF << FPSID_PART_BIT) #define FPSID_VARIANT_BIT (4) @@ -75,6 +76,10 @@ /* MVFR0 bits */ #define MVFR0_A_SIMD_BIT (0) #define MVFR0_A_SIMD_MASK (0xf << MVFR0_A_SIMD_BIT) +#define MVFR0_SP_BIT (4) +#define MVFR0_SP_MASK (0xf << MVFR0_SP_BIT) +#define MVFR0_DP_BIT (8) +#define MVFR0_DP_MASK (0xf << MVFR0_DP_BIT) /* Bit patterns for decoding the packaged operation descriptors */ #define VFPOPDESC_LENGTH_BIT (9) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 2f37e1d6cb45..5002d002f6e3 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -722,6 +722,7 @@ static int __init vfp_init(void) { unsigned int vfpsid; unsigned int cpu_arch = cpu_architecture(); + u32 mvfr0; if (cpu_arch >= CPU_ARCH_ARMv6) on_each_cpu(vfp_enable, NULL, 1); @@ -738,63 +739,73 @@ static int __init vfp_init(void) vfp_vector = vfp_null_entry; pr_info("VFP support v0.3: "); - if (VFP_arch) + if (VFP_arch) { pr_cont("not present\n"); - else if (vfpsid & FPSID_NODOUBLE) { - pr_cont("no double precision support\n"); - } else { - hotcpu_notifier(vfp_hotplug, 0); - - VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT; /* Extract the architecture version */ - pr_cont("implementor %02x architecture %d part %02x variant %x rev %x\n", - (vfpsid & FPSID_IMPLEMENTER_MASK) >> FPSID_IMPLEMENTER_BIT, - (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT, - (vfpsid & FPSID_PART_MASK) >> FPSID_PART_BIT, - (vfpsid & FPSID_VARIANT_MASK) >> FPSID_VARIANT_BIT, - (vfpsid & FPSID_REV_MASK) >> FPSID_REV_BIT); - - vfp_vector = vfp_support_entry; - - thread_register_notifier(&vfp_notifier_block); - vfp_pm_init(); - - /* - * We detected VFP, and the support code is - * in place; report VFP support to userspace. - */ - elf_hwcap |= HWCAP_VFP; -#ifdef CONFIG_VFPv3 - if (VFP_arch >= 2) { - elf_hwcap |= HWCAP_VFPv3; - - /* - * Check for VFPv3 D16 and VFPv4 D16. CPUs in - * this configuration only have 16 x 64bit - * registers. - */ - if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1) - elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */ - else - elf_hwcap |= HWCAP_VFPD32; - } -#endif + return 0; + /* Extract the architecture on CPUID scheme */ + } else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) { + VFP_arch = vfpsid & FPSID_CPUID_ARCH_MASK; + VFP_arch >>= FPSID_ARCH_BIT; /* * Check for the presence of the Advanced SIMD * load/store instructions, integer and single * precision floating point operations. Only check * for NEON if the hardware has the MVFR registers. */ - if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) { #ifdef CONFIG_NEON - if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100) - elf_hwcap |= HWCAP_NEON; + if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100) + elf_hwcap |= HWCAP_NEON; #endif #ifdef CONFIG_VFPv3 - if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000) - elf_hwcap |= HWCAP_VFPv4; -#endif + mvfr0 = fmrx(MVFR0); + if (((mvfr0 & MVFR0_DP_MASK) >> MVFR0_DP_BIT) == 0x2 || + ((mvfr0 & MVFR0_SP_MASK) >> MVFR0_SP_BIT) == 0x2) { + elf_hwcap |= HWCAP_VFPv3; + /* + * Check for VFPv3 D16 and VFPv4 D16. CPUs in + * this configuration only have 16 x 64bit + * registers. + */ + if ((mvfr0 & MVFR0_A_SIMD_MASK) == 1) + /* also v4-D16 */ + elf_hwcap |= HWCAP_VFPv3D16; + else + elf_hwcap |= HWCAP_VFPD32; } + + if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000) + elf_hwcap |= HWCAP_VFPv4; +#endif + /* Extract the architecture version on pre-cpuid scheme */ + } else { + if (vfpsid & FPSID_NODOUBLE) { + pr_cont("no double precision support\n"); + return 0; + } + + VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT; } + + hotcpu_notifier(vfp_hotplug, 0); + + vfp_vector = vfp_support_entry; + + thread_register_notifier(&vfp_notifier_block); + vfp_pm_init(); + + /* + * We detected VFP, and the support code is + * in place; report VFP support to userspace. + */ + elf_hwcap |= HWCAP_VFP; + + pr_cont("implementor %02x architecture %d part %02x variant %x rev %x\n", + (vfpsid & FPSID_IMPLEMENTER_MASK) >> FPSID_IMPLEMENTER_BIT, + VFP_arch, + (vfpsid & FPSID_PART_MASK) >> FPSID_PART_BIT, + (vfpsid & FPSID_VARIANT_MASK) >> FPSID_VARIANT_BIT, + (vfpsid & FPSID_REV_MASK) >> FPSID_REV_BIT); + return 0; } From 2b94fe2ac97fdd2ae7521004e857e33016720eb7 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 20 Nov 2014 20:29:09 +0100 Subject: [PATCH 24/62] ARM: 8215/1: vfp: Silence mvfr0 variable unused warning Stephen Rothwell reports that commit 3f4c9f8f0a20 ("ARM: 8197/1: vfp: Fix VFPv3 hwcap detection on CPUID based cpus") introduced a variable unused warning. arch/arm/vfp/vfpmodule.c: In function 'vfp_init': arch/arm/vfp/vfpmodule.c:725:6: warning: unused variable 'mvfr0' [-Wunused-variable] u32 mvfr0; Silence this warning by using IS_ENABLED instead of ifdefs. Reported-by: Stephen Rothwell Signed-off-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/vfp/vfpmodule.c | 45 ++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 23 deletions(-) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 5002d002f6e3..f6e4d56eda00 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -722,7 +722,6 @@ static int __init vfp_init(void) { unsigned int vfpsid; unsigned int cpu_arch = cpu_architecture(); - u32 mvfr0; if (cpu_arch >= CPU_ARCH_ARMv6) on_each_cpu(vfp_enable, NULL, 1); @@ -752,30 +751,30 @@ static int __init vfp_init(void) * precision floating point operations. Only check * for NEON if the hardware has the MVFR registers. */ -#ifdef CONFIG_NEON - if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100) + if (IS_ENABLED(CONFIG_NEON) && + (fmrx(MVFR1) & 0x000fff00) == 0x00011100) elf_hwcap |= HWCAP_NEON; -#endif -#ifdef CONFIG_VFPv3 - mvfr0 = fmrx(MVFR0); - if (((mvfr0 & MVFR0_DP_MASK) >> MVFR0_DP_BIT) == 0x2 || - ((mvfr0 & MVFR0_SP_MASK) >> MVFR0_SP_BIT) == 0x2) { - elf_hwcap |= HWCAP_VFPv3; - /* - * Check for VFPv3 D16 and VFPv4 D16. CPUs in - * this configuration only have 16 x 64bit - * registers. - */ - if ((mvfr0 & MVFR0_A_SIMD_MASK) == 1) - /* also v4-D16 */ - elf_hwcap |= HWCAP_VFPv3D16; - else - elf_hwcap |= HWCAP_VFPD32; - } - if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000) - elf_hwcap |= HWCAP_VFPv4; -#endif + if (IS_ENABLED(CONFIG_VFPv3)) { + u32 mvfr0 = fmrx(MVFR0); + if (((mvfr0 & MVFR0_DP_MASK) >> MVFR0_DP_BIT) == 0x2 || + ((mvfr0 & MVFR0_SP_MASK) >> MVFR0_SP_BIT) == 0x2) { + elf_hwcap |= HWCAP_VFPv3; + /* + * Check for VFPv3 D16 and VFPv4 D16. CPUs in + * this configuration only have 16 x 64bit + * registers. + */ + if ((mvfr0 & MVFR0_A_SIMD_MASK) == 1) + /* also v4-D16 */ + elf_hwcap |= HWCAP_VFPv3D16; + else + elf_hwcap |= HWCAP_VFPD32; + } + + if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000) + elf_hwcap |= HWCAP_VFPv4; + } /* Extract the architecture version on pre-cpuid scheme */ } else { if (vfpsid & FPSID_NODOUBLE) { From a391263cd84e6ae2da26a54383f3abf80c18d9df Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 14 Nov 2014 11:37:34 +0100 Subject: [PATCH 25/62] ARM: 8203/1: mm: try to re-use old ASID assignments following a rollover Rather than unconditionally allocating a fresh ASID to an mm from an older generation, attempt to re-use the old assignment where possible. This can bring performance benefits on systems where the ASID is used to tag things other than the TLB (e.g. branch prediction resources). Acked-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/mm/context.c | 58 +++++++++++++++++++++++++------------------ 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 6eb97b3a7481..91892569710f 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -184,36 +184,46 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) u64 asid = atomic64_read(&mm->context.id); u64 generation = atomic64_read(&asid_generation); - if (asid != 0 && is_reserved_asid(asid)) { + if (asid != 0) { /* - * Our current ASID was active during a rollover, we can - * continue to use it and this was just a false alarm. + * If our current ASID was active during a rollover, we + * can continue to use it and this was just a false alarm. */ - asid = generation | (asid & ~ASID_MASK); - } else { + if (is_reserved_asid(asid)) + return generation | (asid & ~ASID_MASK); + /* - * Allocate a free ASID. If we can't find one, take a - * note of the currently active ASIDs and mark the TLBs - * as requiring flushes. We always count from ASID #1, - * as we reserve ASID #0 to switch via TTBR0 and to - * avoid speculative page table walks from hitting in - * any partial walk caches, which could be populated - * from overlapping level-1 descriptors used to map both - * the module area and the userspace stack. + * We had a valid ASID in a previous life, so try to re-use + * it if possible., */ - asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx); - if (asid == NUM_USER_ASIDS) { - generation = atomic64_add_return(ASID_FIRST_VERSION, - &asid_generation); - flush_context(cpu); - asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); - } - __set_bit(asid, asid_map); - cur_idx = asid; - asid |= generation; - cpumask_clear(mm_cpumask(mm)); + asid &= ~ASID_MASK; + if (!__test_and_set_bit(asid, asid_map)) + goto bump_gen; } + /* + * Allocate a free ASID. If we can't find one, take a note of the + * currently active ASIDs and mark the TLBs as requiring flushes. + * We always count from ASID #1, as we reserve ASID #0 to switch + * via TTBR0 and to avoid speculative page table walks from hitting + * in any partial walk caches, which could be populated from + * overlapping level-1 descriptors used to map both the module + * area and the userspace stack. + */ + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx); + if (asid == NUM_USER_ASIDS) { + generation = atomic64_add_return(ASID_FIRST_VERSION, + &asid_generation); + flush_context(cpu); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); + } + + __set_bit(asid, asid_map); + cur_idx = asid; + +bump_gen: + asid |= generation; + cpumask_clear(mm_cpumask(mm)); return asid; } From c2459d35f5b8de077fde859b8c96a23f309b9ab2 Mon Sep 17 00:00:00 2001 From: Lin Yongting Date: Sun, 16 Nov 2014 03:14:58 +0100 Subject: [PATCH 26/62] ARM: 8204/1: Add unwinding support for memset function The memset function never had unwinding annotations added. Currently, when accessing NULL pointer by memset occurs the backtrace shown will stop at memset or some completely unrelated function. Add unwinding annotations in hopes of getting a more useful backtrace when accessing NULL pointer by memset, kprobe or interrupt. Signed-off-by: Lin Yongting Signed-off-by: Russell King --- arch/arm/lib/memset.S | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 671455c854fa..a4ee97b5a2bf 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -11,11 +11,13 @@ */ #include #include +#include .text .align 5 ENTRY(memset) +UNWIND( .fnstart ) ands r3, r0, #3 @ 1 unaligned? mov ip, r0 @ preserve r0 as return value bne 6f @ 1 @@ -34,6 +36,9 @@ ENTRY(memset) * We need 2 extra registers for this loop - use r8 and the LR */ stmfd sp!, {r8, lr} +UNWIND( .fnend ) +UNWIND( .fnstart ) +UNWIND( .save {r8, lr} ) mov r8, r1 mov lr, r1 @@ -53,6 +58,7 @@ ENTRY(memset) tst r2, #16 stmneia ip!, {r1, r3, r8, lr} ldmfd sp!, {r8, lr} +UNWIND( .fnend ) #else @@ -62,6 +68,9 @@ ENTRY(memset) */ stmfd sp!, {r4-r8, lr} +UNWIND( .fnend ) +UNWIND( .fnstart ) +UNWIND( .save {r4-r8, lr} ) mov r4, r1 mov r5, r1 mov r6, r1 @@ -94,9 +103,11 @@ ENTRY(memset) tst r2, #16 stmneia ip!, {r4-r7} ldmfd sp!, {r4-r8, lr} +UNWIND( .fnend ) #endif +UNWIND( .fnstart ) 4: tst r2, #8 stmneia ip!, {r1, r3} tst r2, #4 @@ -120,4 +131,5 @@ ENTRY(memset) strb r1, [ip], #1 @ 1 add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) b 1b +UNWIND( .fnend ) ENDPROC(memset) From 4ed89f2228061422ce5f62545fd0b6f6648bd2cc Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 11:26:42 +0000 Subject: [PATCH 27/62] ARM: convert printk(KERN_* to pr_* Convert many (but not all) printk(KERN_* to pr_* to simplify the code. We take the opportunity to join some printk lines together so we don't split the message across several lines, and we also add a few levels to some messages which were previously missing them. Tested-by: Andrew Lunn Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/common/sa1111.c | 13 +++++----- arch/arm/kernel/atags_compat.c | 6 ++--- arch/arm/kernel/atags_parse.c | 5 ++-- arch/arm/kernel/atags_proc.c | 4 ++-- arch/arm/kernel/bios32.c | 2 +- arch/arm/kernel/dma-isa.c | 4 ++-- arch/arm/kernel/dma.c | 26 +++++++++----------- arch/arm/kernel/etm.c | 12 +++++----- arch/arm/kernel/fiq.c | 2 +- arch/arm/kernel/irq.c | 2 +- arch/arm/kernel/machine_kexec.c | 6 ++--- arch/arm/kernel/module.c | 2 +- arch/arm/kernel/smp.c | 16 ++++++------- arch/arm/kernel/smp_twd.c | 4 ++-- arch/arm/kernel/swp_emulate.c | 2 +- arch/arm/kernel/thumbee.c | 2 +- arch/arm/kernel/topology.c | 4 ++-- arch/arm/kernel/traps.c | 42 ++++++++++++++++----------------- arch/arm/kernel/xscale-cp0.c | 7 +++--- arch/arm/mm/alignment.c | 10 ++++---- arch/arm/mm/cache-feroceon-l2.c | 6 ++--- arch/arm/mm/cache-tauros2.c | 12 +++++----- arch/arm/mm/fault-armv.c | 6 ++--- arch/arm/mm/fault.c | 31 ++++++++++++------------ arch/arm/mm/init.c | 4 ++-- arch/arm/mm/mmu.c | 38 ++++++++++++----------------- arch/arm/nwfpe/fpmodule.c | 4 ++-- arch/arm/vfp/vfpsingle.c | 2 +- 28 files changed, 128 insertions(+), 146 deletions(-) diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index e57d7e5bf96a..7b69c5f9cd74 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -282,8 +282,8 @@ static int sa1111_retrigger_lowirq(struct irq_data *d) } if (i == 8) - printk(KERN_ERR "Danger Will Robinson: failed to " - "re-trigger IRQ%d\n", d->irq); + pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n", + d->irq); return i == 8 ? -1 : 0; } @@ -384,8 +384,8 @@ static int sa1111_retrigger_highirq(struct irq_data *d) } if (i == 8) - printk(KERN_ERR "Danger Will Robinson: failed to " - "re-trigger IRQ%d\n", d->irq); + pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n", + d->irq); return i == 8 ? -1 : 0; } @@ -740,9 +740,8 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq) goto err_unmap; } - printk(KERN_INFO "SA1111 Microprocessor Companion Chip: " - "silicon revision %lx, metal revision %lx\n", - (id & SKID_SIREV_MASK)>>4, (id & SKID_MTREV_MASK)); + pr_info("SA1111 Microprocessor Companion Chip: silicon revision %lx, metal revision %lx\n", + (id & SKID_SIREV_MASK) >> 4, id & SKID_MTREV_MASK); /* * We found it. Wake the chip up, and initialise. diff --git a/arch/arm/kernel/atags_compat.c b/arch/arm/kernel/atags_compat.c index 5236ad38f417..05c28b12353c 100644 --- a/arch/arm/kernel/atags_compat.c +++ b/arch/arm/kernel/atags_compat.c @@ -97,8 +97,7 @@ static void __init build_tag_list(struct param_struct *params, void *taglist) struct tag *tag = taglist; if (params->u1.s.page_size != PAGE_SIZE) { - printk(KERN_WARNING "Warning: bad configuration page, " - "trying to continue\n"); + pr_warn("Warning: bad configuration page, trying to continue\n"); return; } @@ -109,8 +108,7 @@ static void __init build_tag_list(struct param_struct *params, void *taglist) params->u1.s.nr_pages != 0x04000 && params->u1.s.nr_pages != 0x08000 && params->u1.s.nr_pages != 0x10000) { - printk(KERN_WARNING "Warning: bad NeTTrom parameters " - "detected, using defaults\n"); + pr_warn("Warning: bad NeTTrom parameters detected, using defaults\n"); params->u1.s.nr_pages = 0x1000; /* 16MB */ params->u1.s.ramdisk_size = 0; diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c index 528f8af2addb..68c6ae0b9e4c 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -167,8 +167,7 @@ static void __init parse_tags(const struct tag *t) { for (; t->hdr.size; t = tag_next(t)) if (!parse_tag(t)) - printk(KERN_WARNING - "Ignoring unrecognised tag 0x%08x\n", + pr_warn("Ignoring unrecognised tag 0x%08x\n", t->hdr.tag); } @@ -193,7 +192,7 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) */ for_each_machine_desc(p) if (machine_nr == p->nr) { - printk("Machine: %s\n", p->name); + pr_info("Machine: %s\n", p->name); mdesc = p; break; } diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c index c7ff8073416f..5a3379055f55 100644 --- a/arch/arm/kernel/atags_proc.c +++ b/arch/arm/kernel/atags_proc.c @@ -41,7 +41,7 @@ static int __init init_atags_procfs(void) size_t size; if (tag->hdr.tag != ATAG_CORE) { - printk(KERN_INFO "No ATAGs?"); + pr_info("No ATAGs?"); return -EINVAL; } @@ -68,7 +68,7 @@ static int __init init_atags_procfs(void) nomem: kfree(b); - printk(KERN_ERR "Exporting ATAGs: not enough memory\n"); + pr_err("Exporting ATAGs: not enough memory\n"); return -ENOMEM; } diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 17a26c17f7f5..391ffdfce571 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -355,7 +355,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) /* * Report what we did for this bus */ - printk(KERN_INFO "PCI: bus%d: Fast back to back transfers %sabled\n", + pr_info("PCI: bus%d: Fast back to back transfers %sabled\n", bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis"); } EXPORT_SYMBOL(pcibios_fixup_bus); diff --git a/arch/arm/kernel/dma-isa.c b/arch/arm/kernel/dma-isa.c index 360bb6d701f5..84363fe7bad2 100644 --- a/arch/arm/kernel/dma-isa.c +++ b/arch/arm/kernel/dma-isa.c @@ -213,8 +213,8 @@ void __init isa_init_dma(void) for (chan = 0; chan < 8; chan++) { int ret = isa_dma_add(chan, &isa_dma[chan]); if (ret) - printk(KERN_ERR "ISADMA%u: unable to register: %d\n", - chan, ret); + pr_err("ISADMA%u: unable to register: %d\n", + chan, ret); } request_dma(DMA_ISA_CASCADE, "cascade"); diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c index 7b829d9663b1..e651c4d0a0d9 100644 --- a/arch/arm/kernel/dma.c +++ b/arch/arm/kernel/dma.c @@ -79,7 +79,7 @@ int request_dma(unsigned int chan, const char *device_id) return ret; bad_dma: - printk(KERN_ERR "dma: trying to allocate DMA%d\n", chan); + pr_err("dma: trying to allocate DMA%d\n", chan); return -EINVAL; busy: @@ -100,7 +100,7 @@ void free_dma(unsigned int chan) goto bad_dma; if (dma->active) { - printk(KERN_ERR "dma%d: freeing active DMA\n", chan); + pr_err("dma%d: freeing active DMA\n", chan); dma->d_ops->disable(chan, dma); dma->active = 0; } @@ -111,11 +111,11 @@ void free_dma(unsigned int chan) return; } - printk(KERN_ERR "dma%d: trying to free free DMA\n", chan); + pr_err("dma%d: trying to free free DMA\n", chan); return; bad_dma: - printk(KERN_ERR "dma: trying to free DMA%d\n", chan); + pr_err("dma: trying to free DMA%d\n", chan); } EXPORT_SYMBOL(free_dma); @@ -126,8 +126,7 @@ void set_dma_sg (unsigned int chan, struct scatterlist *sg, int nr_sg) dma_t *dma = dma_channel(chan); if (dma->active) - printk(KERN_ERR "dma%d: altering DMA SG while " - "DMA active\n", chan); + pr_err("dma%d: altering DMA SG while DMA active\n", chan); dma->sg = sg; dma->sgcount = nr_sg; @@ -144,8 +143,7 @@ void __set_dma_addr (unsigned int chan, void *addr) dma_t *dma = dma_channel(chan); if (dma->active) - printk(KERN_ERR "dma%d: altering DMA address while " - "DMA active\n", chan); + pr_err("dma%d: altering DMA address while DMA active\n", chan); dma->sg = NULL; dma->addr = addr; @@ -162,8 +160,7 @@ void set_dma_count (unsigned int chan, unsigned long count) dma_t *dma = dma_channel(chan); if (dma->active) - printk(KERN_ERR "dma%d: altering DMA count while " - "DMA active\n", chan); + pr_err("dma%d: altering DMA count while DMA active\n", chan); dma->sg = NULL; dma->count = count; @@ -178,8 +175,7 @@ void set_dma_mode (unsigned int chan, unsigned int mode) dma_t *dma = dma_channel(chan); if (dma->active) - printk(KERN_ERR "dma%d: altering DMA mode while " - "DMA active\n", chan); + pr_err("dma%d: altering DMA mode while DMA active\n", chan); dma->dma_mode = mode; dma->invalid = 1; @@ -202,7 +198,7 @@ void enable_dma (unsigned int chan) return; free_dma: - printk(KERN_ERR "dma%d: trying to enable free DMA\n", chan); + pr_err("dma%d: trying to enable free DMA\n", chan); BUG(); } EXPORT_SYMBOL(enable_dma); @@ -223,7 +219,7 @@ void disable_dma (unsigned int chan) return; free_dma: - printk(KERN_ERR "dma%d: trying to disable free DMA\n", chan); + pr_err("dma%d: trying to disable free DMA\n", chan); BUG(); } EXPORT_SYMBOL(disable_dma); @@ -240,7 +236,7 @@ EXPORT_SYMBOL(dma_channel_active); void set_dma_page(unsigned int chan, char pagenr) { - printk(KERN_ERR "dma%d: trying to set_dma_page\n", chan); + pr_err("dma%d: trying to set_dma_page\n", chan); } EXPORT_SYMBOL(set_dma_page); diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c index 131a6ab5f355..8b96972dcb1d 100644 --- a/arch/arm/kernel/etm.c +++ b/arch/arm/kernel/etm.c @@ -213,7 +213,7 @@ static void etm_dump(void) int length; if (!t->etb_regs) { - printk(KERN_INFO "No tracing hardware found\n"); + pr_info("No tracing hardware found\n"); return; } @@ -229,11 +229,11 @@ static void etm_dump(void) etb_writel(t, first, ETBR_READADDR); - printk(KERN_INFO "Trace buffer contents length: %d\n", length); - printk(KERN_INFO "--- ETB buffer begin ---\n"); + pr_info("Trace buffer contents length: %d\n", length); + pr_info("--- ETB buffer begin ---\n"); for (; length; length--) printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM))); - printk(KERN_INFO "\n--- ETB buffer end ---\n"); + pr_info("\n--- ETB buffer end ---\n"); /* deassert the overflow bit */ etb_writel(t, 1, ETBR_CTRL); @@ -633,14 +633,14 @@ static int __init etm_init(void) retval = amba_driver_register(&etb_driver); if (retval) { - printk(KERN_ERR "Failed to register etb\n"); + pr_err("Failed to register etb\n"); return retval; } retval = amba_driver_register(&etm_driver); if (retval) { amba_driver_unregister(&etb_driver); - printk(KERN_ERR "Failed to probe etm\n"); + pr_err("Failed to probe etm\n"); return retval; } diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index b37752a96652..059c3da0fee3 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -124,7 +124,7 @@ int claim_fiq(struct fiq_handler *f) void release_fiq(struct fiq_handler *f) { if (current_fiq != f) { - printk(KERN_ERR "%s FIQ trying to release %s FIQ\n", + pr_err("%s FIQ trying to release %s FIQ\n", f->name, current_fiq->name); dump_stack(); return; diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 7c81ec428b9b..f2fea6831cd5 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -82,7 +82,7 @@ void set_irq_flags(unsigned int irq, unsigned int iflags) unsigned long clr = 0, set = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; if (irq >= nr_irqs) { - printk(KERN_ERR "Trying to set irq flags for IRQ%d\n", irq); + pr_err("Trying to set irq flags for IRQ%d\n", irq); return; } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 8cf0996aa1a8..4f75192f2ef9 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -126,12 +126,12 @@ void machine_crash_shutdown(struct pt_regs *regs) msecs--; } if (atomic_read(&waiting_for_crash_ipi) > 0) - printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n"); + pr_warn("Non-crashing CPUs did not react to IPI\n"); crash_save_cpu(regs, smp_processor_id()); machine_kexec_mask_interrupts(); - printk(KERN_INFO "Loading crashdump kernel...\n"); + pr_info("Loading crashdump kernel...\n"); } /* @@ -177,7 +177,7 @@ void machine_kexec(struct kimage *image) reboot_entry_phys = (unsigned long)reboot_entry + (reboot_code_buffer_phys - (unsigned long)reboot_code_buffer); - printk(KERN_INFO "Bye!\n"); + pr_info("Bye!\n"); if (kexec_reinit) kexec_reinit(); diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 6a4dffefd357..bea7db9e5b80 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -251,7 +251,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, #endif default: - printk(KERN_ERR "%s: unknown relocation: %u\n", + pr_err("%s: unknown relocation: %u\n", module->name, ELF32_R_TYPE(rel->r_info)); return -ENOEXEC; } diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 13396d3d600e..3138d8ea9e55 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -225,7 +225,7 @@ void __cpu_die(unsigned int cpu) pr_err("CPU%u: cpu didn't die\n", cpu); return; } - printk(KERN_NOTICE "CPU%u: shutdown\n", cpu); + pr_notice("CPU%u: shutdown\n", cpu); /* * platform_cpu_kill() is generally expected to do the powering off @@ -235,7 +235,7 @@ void __cpu_die(unsigned int cpu) * the requesting CPU and the dying CPU actually losing power. */ if (!platform_cpu_kill(cpu)) - printk("CPU%u: unable to kill\n", cpu); + pr_err("CPU%u: unable to kill\n", cpu); } /* @@ -351,7 +351,7 @@ asmlinkage void secondary_start_kernel(void) cpu_init(); - printk("CPU%u: Booted secondary processor\n", cpu); + pr_info("CPU%u: Booted secondary processor\n", cpu); preempt_disable(); trace_hardirqs_off(); @@ -387,8 +387,8 @@ asmlinkage void secondary_start_kernel(void) void __init smp_cpus_done(unsigned int max_cpus) { - printk(KERN_INFO "SMP: Total of %d processors activated.\n", - num_online_cpus()); + pr_info("SMP: Total of %d processors activated.\n", + num_online_cpus()); hyp_mode_check(); } @@ -521,7 +521,7 @@ static void ipi_cpu_stop(unsigned int cpu) if (system_state == SYSTEM_BOOTING || system_state == SYSTEM_RUNNING) { raw_spin_lock(&stop_lock); - printk(KERN_CRIT "CPU%u: stopping\n", cpu); + pr_crit("CPU%u: stopping\n", cpu); dump_stack(); raw_spin_unlock(&stop_lock); } @@ -615,8 +615,8 @@ void handle_IPI(int ipinr, struct pt_regs *regs) break; default: - printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", - cpu, ipinr); + pr_crit("CPU%u: Unknown IPI message 0x%x\n", + cpu, ipinr); break; } diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 93090213c71c..172c6a05d27f 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -199,7 +199,7 @@ static void twd_calibrate_rate(void) * the timer ticks */ if (twd_timer_rate == 0) { - printk(KERN_INFO "Calibrating local timer... "); + pr_info("Calibrating local timer... "); /* Wait for a tick to start */ waitjiffies = get_jiffies_64() + 1; @@ -223,7 +223,7 @@ static void twd_calibrate_rate(void) twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); - printk("%lu.%02luMHz.\n", twd_timer_rate / 1000000, + pr_cont("%lu.%02luMHz.\n", twd_timer_rate / 1000000, (twd_timer_rate / 10000) % 100); } } diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 587fdfe1a72c..afdd51e30bec 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -260,7 +260,7 @@ static int __init swp_emulation_init(void) return -ENOMEM; #endif /* CONFIG_PROC_FS */ - printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n"); + pr_notice("Registering SWP/SWPB emulation handler\n"); register_undef_hook(&swp_hook); return 0; diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c index 80f0d69205e7..8ff8dbfbe9fb 100644 --- a/arch/arm/kernel/thumbee.c +++ b/arch/arm/kernel/thumbee.c @@ -72,7 +72,7 @@ static int __init thumbee_init(void) if ((pfr0 & 0x0000f000) != 0x00001000) return 0; - printk(KERN_INFO "ThumbEE CPU extension supported.\n"); + pr_info("ThumbEE CPU extension supported.\n"); elf_hwcap |= HWCAP_THUMBEE; thread_register_notifier(&thumbee_notifier_block); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 89cfdd6e50cb..08b7847bf912 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -165,7 +165,7 @@ static void update_cpu_capacity(unsigned int cpu) set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); - printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n", + pr_info("CPU%u: update cpu_capacity %lu\n", cpu, arch_scale_cpu_capacity(NULL, cpu)); } @@ -269,7 +269,7 @@ void store_cpu_topology(unsigned int cpuid) update_cpu_capacity(cpuid); - printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", + pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, cpu_topology[cpuid].core_id, cpu_topology[cpuid].socket_id, mpidr); diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 0c8b10801d36..bb121b52ef36 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -198,14 +198,14 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) } if (!fp) { - printk("no frame pointer"); + pr_cont("no frame pointer"); ok = 0; } else if (verify_stack(fp)) { - printk("invalid frame pointer 0x%08x", fp); + pr_cont("invalid frame pointer 0x%08x", fp); ok = 0; } else if (fp < (unsigned long)end_of_stack(tsk)) - printk("frame pointer underflow"); - printk("\n"); + pr_cont("frame pointer underflow"); + pr_cont("\n"); if (ok) c_backtrace(fp, mode); @@ -240,8 +240,8 @@ static int __die(const char *str, int err, struct pt_regs *regs) static int die_counter; int ret; - printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP - S_ISA "\n", str, err, ++die_counter); + pr_emerg("Internal error: %s: %x [#%d]" S_PREEMPT S_SMP S_ISA "\n", + str, err, ++die_counter); /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV); @@ -250,8 +250,8 @@ static int __die(const char *str, int err, struct pt_regs *regs) print_modules(); __show_regs(regs); - printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n", - TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); + pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", + TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp, @@ -446,7 +446,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) die_sig: #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_UNDEFINED) { - printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n", + pr_info("%s (%d): undefined instruction: pc=%p\n", current->comm, task_pid_nr(current), pc); __show_regs(regs); dump_instr(KERN_INFO, regs); @@ -496,7 +496,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason) { console_verbose(); - printk(KERN_CRIT "Bad mode in %s handler detected\n", handler[reason]); + pr_crit("Bad mode in %s handler detected\n", handler[reason]); die("Oops - bad mode", regs, 0); local_irq_disable(); @@ -516,7 +516,7 @@ static int bad_syscall(int n, struct pt_regs *regs) #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_SYSCALL) { - printk(KERN_ERR "[%d] %s: obsolete system call %08x.\n", + pr_err("[%d] %s: obsolete system call %08x.\n", task_pid_nr(current), current->comm, n); dump_instr(KERN_ERR, regs); } @@ -721,7 +721,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) * something catastrophic has happened */ if (user_debug & UDBG_SYSCALL) { - printk("[%d] %s: arm syscall %d\n", + pr_err("[%d] %s: arm syscall %d\n", task_pid_nr(current), current->comm, no); dump_instr("", regs); if (user_mode(regs)) { @@ -780,8 +780,8 @@ late_initcall(arm_mrc_hook_init); void __bad_xchg(volatile void *ptr, int size) { - printk("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n", - __builtin_return_address(0), ptr, size); + pr_err("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n", + __builtin_return_address(0), ptr, size); BUG(); } EXPORT_SYMBOL(__bad_xchg); @@ -798,8 +798,8 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs) #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_BADABORT) { - printk(KERN_ERR "[%d] %s: bad data abort: code %d instr 0x%08lx\n", - task_pid_nr(current), current->comm, code, instr); + pr_err("[%d] %s: bad data abort: code %d instr 0x%08lx\n", + task_pid_nr(current), current->comm, code, instr); dump_instr(KERN_ERR, regs); show_pte(current->mm, addr); } @@ -815,29 +815,29 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs) void __readwrite_bug(const char *fn) { - printk("%s called, but not implemented\n", fn); + pr_err("%s called, but not implemented\n", fn); BUG(); } EXPORT_SYMBOL(__readwrite_bug); void __pte_error(const char *file, int line, pte_t pte) { - printk("%s:%d: bad pte %08llx.\n", file, line, (long long)pte_val(pte)); + pr_err("%s:%d: bad pte %08llx.\n", file, line, (long long)pte_val(pte)); } void __pmd_error(const char *file, int line, pmd_t pmd) { - printk("%s:%d: bad pmd %08llx.\n", file, line, (long long)pmd_val(pmd)); + pr_err("%s:%d: bad pmd %08llx.\n", file, line, (long long)pmd_val(pmd)); } void __pgd_error(const char *file, int line, pgd_t pgd) { - printk("%s:%d: bad pgd %08llx.\n", file, line, (long long)pgd_val(pgd)); + pr_err("%s:%d: bad pgd %08llx.\n", file, line, (long long)pgd_val(pgd)); } asmlinkage void __div0(void) { - printk("Division by zero in kernel.\n"); + pr_err("Division by zero in kernel.\n"); dump_stack(); } EXPORT_SYMBOL(__div0); diff --git a/arch/arm/kernel/xscale-cp0.c b/arch/arm/kernel/xscale-cp0.c index e42adc6bcdb1..bdbb8853a19b 100644 --- a/arch/arm/kernel/xscale-cp0.c +++ b/arch/arm/kernel/xscale-cp0.c @@ -157,15 +157,14 @@ static int __init xscale_cp0_init(void) if (cpu_has_iwmmxt()) { #ifndef CONFIG_IWMMXT - printk(KERN_WARNING "CAUTION: XScale iWMMXt coprocessor " - "detected, but kernel support is missing.\n"); + pr_warn("CAUTION: XScale iWMMXt coprocessor detected, but kernel support is missing.\n"); #else - printk(KERN_INFO "XScale iWMMXt coprocessor detected.\n"); + pr_info("XScale iWMMXt coprocessor detected.\n"); elf_hwcap |= HWCAP_IWMMXT; thread_register_notifier(&iwmmxt_notifier_block); #endif } else { - printk(KERN_INFO "XScale DSP coprocessor detected.\n"); + pr_info("XScale DSP coprocessor detected.\n"); thread_register_notifier(&dsp_notifier_block); cp_access |= 1; } diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 83792f4324ea..2c0c541c60ca 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -113,7 +113,7 @@ static int safe_usermode(int new_usermode, bool warn) new_usermode |= UM_FIXUP; if (warn) - printk(KERN_WARNING "alignment: ignoring faults is unsafe on this CPU. Defaulting to fixup mode.\n"); + pr_warn("alignment: ignoring faults is unsafe on this CPU. Defaulting to fixup mode.\n"); } return new_usermode; @@ -523,7 +523,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg * processor for us. */ if (addr != eaddr) { - printk(KERN_ERR "LDMSTM: PC = %08lx, instr = %08lx, " + pr_err("LDMSTM: PC = %08lx, instr = %08lx, " "addr = %08lx, eaddr = %08lx\n", instruction_pointer(regs), instr, addr, eaddr); show_regs(regs); @@ -567,7 +567,7 @@ fault: return TYPE_FAULT; bad: - printk(KERN_ERR "Alignment trap: not handling ldm with s-bit set\n"); + pr_err("Alignment trap: not handling ldm with s-bit set\n"); return TYPE_ERROR; } @@ -899,13 +899,13 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; swp: - printk(KERN_ERR "Alignment trap: not handling swp instruction\n"); + pr_err("Alignment trap: not handling swp instruction\n"); bad: /* * Oops, we didn't handle the instruction. */ - printk(KERN_ERR "Alignment trap: not handling instruction " + pr_err("Alignment trap: not handling instruction " "%0*lx at [<%08lx>]\n", isize << 1, isize == 2 ? tinstr : instr, instrptr); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index e028a7f2ebcc..097181e08c25 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -313,7 +313,7 @@ static void __init disable_l2_prefetch(void) */ u = read_extra_features(); if (!(u & 0x01000000)) { - printk(KERN_INFO "Feroceon L2: Disabling L2 prefetch.\n"); + pr_info("Feroceon L2: Disabling L2 prefetch.\n"); write_extra_features(u | 0x01000000); } } @@ -326,7 +326,7 @@ static void __init enable_l2(void) if (!(u & 0x00400000)) { int i, d; - printk(KERN_INFO "Feroceon L2: Enabling L2\n"); + pr_info("Feroceon L2: Enabling L2\n"); d = flush_and_disable_dcache(); i = invalidate_and_disable_icache(); @@ -353,7 +353,7 @@ void __init feroceon_l2_init(int __l2_wt_override) enable_l2(); - printk(KERN_INFO "Feroceon L2: Cache support initialised%s.\n", + pr_info("Feroceon L2: Cache support initialised%s.\n", l2_wt_override ? ", in WT override mode" : ""); } #ifdef CONFIG_OF diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c index b273739e6359..1e373d268c04 100644 --- a/arch/arm/mm/cache-tauros2.c +++ b/arch/arm/mm/cache-tauros2.c @@ -185,7 +185,7 @@ static void enable_extra_feature(unsigned int features) u &= ~0x01000000; else u |= 0x01000000; - printk(KERN_INFO "Tauros2: %s L2 prefetch.\n", + pr_info("Tauros2: %s L2 prefetch.\n", (features & CACHE_TAUROS2_PREFETCH_ON) ? "Enabling" : "Disabling"); @@ -193,7 +193,7 @@ static void enable_extra_feature(unsigned int features) u |= 0x00100000; else u &= ~0x00100000; - printk(KERN_INFO "Tauros2: %s line fill burt8.\n", + pr_info("Tauros2: %s line fill burt8.\n", (features & CACHE_TAUROS2_LINEFILL_BURST8) ? "Enabling" : "Disabling"); @@ -216,7 +216,7 @@ static void __init tauros2_internal_init(unsigned int features) */ feat = read_extra_features(); if (!(feat & 0x00400000)) { - printk(KERN_INFO "Tauros2: Enabling L2 cache.\n"); + pr_info("Tauros2: Enabling L2 cache.\n"); write_extra_features(feat | 0x00400000); } @@ -253,7 +253,7 @@ static void __init tauros2_internal_init(unsigned int features) */ actlr = read_actlr(); if (!(actlr & 0x00000002)) { - printk(KERN_INFO "Tauros2: Enabling L2 cache.\n"); + pr_info("Tauros2: Enabling L2 cache.\n"); write_actlr(actlr | 0x00000002); } @@ -262,11 +262,11 @@ static void __init tauros2_internal_init(unsigned int features) #endif if (mode == NULL) { - printk(KERN_CRIT "Tauros2: Unable to detect CPU mode.\n"); + pr_crit("Tauros2: Unable to detect CPU mode.\n"); return; } - printk(KERN_INFO "Tauros2: L2 cache support initialised " + pr_info("Tauros2: L2 cache support initialised " "in %s mode.\n", mode); } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index ff379ac115df..d9e0d00a6699 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -235,7 +235,7 @@ void __init check_writebuffer_bugs(void) const char *reason; unsigned long v = 1; - printk(KERN_INFO "CPU: Testing write buffer coherency: "); + pr_info("CPU: Testing write buffer coherency: "); page = alloc_page(GFP_KERNEL); if (page) { @@ -261,9 +261,9 @@ void __init check_writebuffer_bugs(void) } if (v) { - printk("failed, %s\n", reason); + pr_cont("failed, %s\n", reason); shared_pte_mask = L_PTE_MT_UNCACHED; } else { - printk("ok\n"); + pr_cont("ok\n"); } } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index eb8830a4c5ed..a982dc3190df 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -63,9 +63,9 @@ void show_pte(struct mm_struct *mm, unsigned long addr) if (!mm) mm = &init_mm; - printk(KERN_ALERT "pgd = %p\n", mm->pgd); + pr_alert("pgd = %p\n", mm->pgd); pgd = pgd_offset(mm, addr); - printk(KERN_ALERT "[%08lx] *pgd=%08llx", + pr_alert("[%08lx] *pgd=%08llx", addr, (long long)pgd_val(*pgd)); do { @@ -77,31 +77,31 @@ void show_pte(struct mm_struct *mm, unsigned long addr) break; if (pgd_bad(*pgd)) { - printk("(bad)"); + pr_cont("(bad)"); break; } pud = pud_offset(pgd, addr); if (PTRS_PER_PUD != 1) - printk(", *pud=%08llx", (long long)pud_val(*pud)); + pr_cont(", *pud=%08llx", (long long)pud_val(*pud)); if (pud_none(*pud)) break; if (pud_bad(*pud)) { - printk("(bad)"); + pr_cont("(bad)"); break; } pmd = pmd_offset(pud, addr); if (PTRS_PER_PMD != 1) - printk(", *pmd=%08llx", (long long)pmd_val(*pmd)); + pr_cont(", *pmd=%08llx", (long long)pmd_val(*pmd)); if (pmd_none(*pmd)) break; if (pmd_bad(*pmd)) { - printk("(bad)"); + pr_cont("(bad)"); break; } @@ -110,15 +110,15 @@ void show_pte(struct mm_struct *mm, unsigned long addr) break; pte = pte_offset_map(pmd, addr); - printk(", *pte=%08llx", (long long)pte_val(*pte)); + pr_cont(", *pte=%08llx", (long long)pte_val(*pte)); #ifndef CONFIG_ARM_LPAE - printk(", *ppte=%08llx", + pr_cont(", *ppte=%08llx", (long long)pte_val(pte[PTE_HWTABLE_PTRS])); #endif pte_unmap(pte); } while(0); - printk("\n"); + pr_cont("\n"); } #else /* CONFIG_MMU */ void show_pte(struct mm_struct *mm, unsigned long addr) @@ -142,10 +142,9 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, * No handler, we'll have to terminate things with extreme prejudice. */ bust_spinlocks(1); - printk(KERN_ALERT - "Unable to handle kernel %s at virtual address %08lx\n", - (addr < PAGE_SIZE) ? "NULL pointer dereference" : - "paging request", addr); + pr_alert("Unable to handle kernel %s at virtual address %08lx\n", + (addr < PAGE_SIZE) ? "NULL pointer dereference" : + "paging request", addr); show_pte(mm, addr); die("Oops", regs, fsr); @@ -551,7 +550,7 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs)) return; - printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n", + pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n", inf->name, fsr, addr); info.si_signo = inf->sig; @@ -583,7 +582,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs) if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs)) return; - printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n", + pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n", inf->name, ifsr, addr); info.si_signo = inf->sig; diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 92bba32d9230..6ca53c338519 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -67,7 +67,7 @@ early_param("initrd", early_initrd); static int __init parse_tag_initrd(const struct tag *tag) { - printk(KERN_WARNING "ATAG_INITRD is deprecated; " + pr_warn("ATAG_INITRD is deprecated; " "please update your bootloader.\n"); phys_initrd_start = __virt_to_phys(tag->u.initrd.start); phys_initrd_size = tag->u.initrd.size; @@ -544,7 +544,7 @@ void __init mem_init(void) #define MLM(b, t) b, t, ((t) - (b)) >> 20 #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K) - printk(KERN_NOTICE "Virtual kernel memory layout:\n" + pr_notice("Virtual kernel memory layout:\n" " vector : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HAVE_TCM " DTCM : 0x%08lx - 0x%08lx (%4ld kB)\n" diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 9f98cec7fe1e..d028dc74a9d5 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -192,7 +192,7 @@ early_param("cachepolicy", early_cachepolicy); static int __init early_nocache(char *__unused) { char *p = "buffered"; - printk(KERN_WARNING "nocache is deprecated; use cachepolicy=%s\n", p); + pr_warn("nocache is deprecated; use cachepolicy=%s\n", p); early_cachepolicy(p); return 0; } @@ -201,7 +201,7 @@ early_param("nocache", early_nocache); static int __init early_nowrite(char *__unused) { char *p = "uncached"; - printk(KERN_WARNING "nowb is deprecated; use cachepolicy=%s\n", p); + pr_warn("nowb is deprecated; use cachepolicy=%s\n", p); early_cachepolicy(p); return 0; } @@ -786,8 +786,7 @@ static void __init create_36bit_mapping(struct map_desc *md, length = PAGE_ALIGN(md->length); if (!(cpu_architecture() >= CPU_ARCH_ARMv6 || cpu_is_xsc3())) { - printk(KERN_ERR "MM: CPU does not support supersection " - "mapping for 0x%08llx at 0x%08lx\n", + pr_err("MM: CPU does not support supersection mapping for 0x%08llx at 0x%08lx\n", (long long)__pfn_to_phys((u64)md->pfn), addr); return; } @@ -799,15 +798,13 @@ static void __init create_36bit_mapping(struct map_desc *md, * of the actual domain assignments in use. */ if (type->domain) { - printk(KERN_ERR "MM: invalid domain in supersection " - "mapping for 0x%08llx at 0x%08lx\n", + pr_err("MM: invalid domain in supersection mapping for 0x%08llx at 0x%08lx\n", (long long)__pfn_to_phys((u64)md->pfn), addr); return; } if ((addr | length | __pfn_to_phys(md->pfn)) & ~SUPERSECTION_MASK) { - printk(KERN_ERR "MM: cannot create mapping for 0x%08llx" - " at 0x%08lx invalid alignment\n", + pr_err("MM: cannot create mapping for 0x%08llx at 0x%08lx invalid alignment\n", (long long)__pfn_to_phys((u64)md->pfn), addr); return; } @@ -850,18 +847,16 @@ static void __init create_mapping(struct map_desc *md) pgd_t *pgd; if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) { - printk(KERN_WARNING "BUG: not creating mapping for 0x%08llx" - " at 0x%08lx in user region\n", - (long long)__pfn_to_phys((u64)md->pfn), md->virtual); + pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n", + (long long)__pfn_to_phys((u64)md->pfn), md->virtual); return; } if ((md->type == MT_DEVICE || md->type == MT_ROM) && md->virtual >= PAGE_OFFSET && (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) { - printk(KERN_WARNING "BUG: mapping for 0x%08llx" - " at 0x%08lx out of vmalloc space\n", - (long long)__pfn_to_phys((u64)md->pfn), md->virtual); + pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n", + (long long)__pfn_to_phys((u64)md->pfn), md->virtual); } type = &mem_types[md->type]; @@ -881,9 +876,8 @@ static void __init create_mapping(struct map_desc *md) length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK)); if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) { - printk(KERN_WARNING "BUG: map for 0x%08llx at 0x%08lx can not " - "be mapped using pages, ignoring.\n", - (long long)__pfn_to_phys(md->pfn), addr); + pr_warn("BUG: map for 0x%08llx at 0x%08lx can not be mapped using pages, ignoring.\n", + (long long)__pfn_to_phys(md->pfn), addr); return; } @@ -1053,15 +1047,13 @@ static int __init early_vmalloc(char *arg) if (vmalloc_reserve < SZ_16M) { vmalloc_reserve = SZ_16M; - printk(KERN_WARNING - "vmalloc area too small, limiting to %luMB\n", + pr_warn("vmalloc area too small, limiting to %luMB\n", vmalloc_reserve >> 20); } if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) { vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M); - printk(KERN_WARNING - "vmalloc area is too big, limiting to %luMB\n", + pr_warn("vmalloc area is too big, limiting to %luMB\n", vmalloc_reserve >> 20); } @@ -1094,7 +1086,7 @@ void __init sanity_check_meminfo(void) if (highmem) { pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", - &block_start, &block_end); + &block_start, &block_end); memblock_remove(reg->base, reg->size); continue; } @@ -1103,7 +1095,7 @@ void __init sanity_check_meminfo(void) phys_addr_t overlap_size = reg->size - size_limit; pr_notice("Truncating RAM at %pa-%pa to -%pa", - &block_start, &block_end, &vmalloc_limit); + &block_start, &block_end, &vmalloc_limit); memblock_remove(vmalloc_limit, overlap_size); block_end = vmalloc_limit; } diff --git a/arch/arm/nwfpe/fpmodule.c b/arch/arm/nwfpe/fpmodule.c index 4e729f055a81..b2a9182acf14 100644 --- a/arch/arm/nwfpe/fpmodule.c +++ b/arch/arm/nwfpe/fpmodule.c @@ -86,12 +86,12 @@ extern void nwfpe_enter(void); static int __init fpe_init(void) { if (sizeof(FPA11) > sizeof(union fp_state)) { - printk(KERN_ERR "nwfpe: bad structure size\n"); + pr_err("nwfpe: bad structure size\n"); return -EINVAL; } if (sizeof(FPREG) != 12) { - printk(KERN_ERR "nwfpe: bad register size\n"); + pr_err("nwfpe: bad register size\n"); return -EINVAL; } if (fpe_type[0] && strcmp(fpe_type, "nwfpe")) diff --git a/arch/arm/vfp/vfpsingle.c b/arch/arm/vfp/vfpsingle.c index 4f96c1617aae..f0465ba0f221 100644 --- a/arch/arm/vfp/vfpsingle.c +++ b/arch/arm/vfp/vfpsingle.c @@ -290,7 +290,7 @@ u32 vfp_estimate_sqrt_significand(u32 exponent, u32 significand) u32 z, a; if ((significand & 0xc0000000) != 0x40000000) { - printk(KERN_WARNING "VFP: estimate_sqrt: invalid significand\n"); + pr_warn("VFP: estimate_sqrt: invalid significand\n"); } a = significand << 1; From 108900b54dce19aab3fa48adde7138ed868bb109 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 13:32:35 +0000 Subject: [PATCH 28/62] ARM: use pr_warn_ratelimited() when migrating IRQs Rather than open coding the printk_ratelimit() check with pr_warn(), use pr_warn_ratelimited() instead. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/irq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index f2fea6831cd5..ad857bada96c 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -135,7 +136,6 @@ int __init arch_probe_nr_irqs(void) #endif #ifdef CONFIG_HOTPLUG_CPU - static bool migrate_one_irq(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); @@ -187,8 +187,8 @@ void migrate_irqs(void) affinity_broken = migrate_one_irq(desc); raw_spin_unlock(&desc->lock); - if (affinity_broken && printk_ratelimit()) - pr_warn("IRQ%u no longer affine to CPU%u\n", + if (affinity_broken) + pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", i, smp_processor_id()); } From 8a2ab42b7586a78d6225771cf65bfb9df50b029f Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 12:06:55 +0000 Subject: [PATCH 29/62] ARM: drop nwfpe initialisation message from warning to info level nwfpe's initialisation message is not a warning, it is purely informational. Print it at the appropriate message level. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/nwfpe/fpmodule.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/nwfpe/fpmodule.c b/arch/arm/nwfpe/fpmodule.c index b2a9182acf14..ec717c190e2c 100644 --- a/arch/arm/nwfpe/fpmodule.c +++ b/arch/arm/nwfpe/fpmodule.c @@ -98,8 +98,8 @@ static int __init fpe_init(void) return 0; /* Display title, version and copyright information. */ - printk(KERN_WARNING "NetWinder Floating Point Emulator V0.97 (" - NWFPE_BITS " precision)\n"); + pr_info("NetWinder Floating Point Emulator V0.97 (" + NWFPE_BITS " precision)\n"); thread_register_notifier(&nwfpe_notifier_block); From c68b0274fb3cf8b98c3696354833c03e49963bf4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 12:08:34 +0000 Subject: [PATCH 30/62] ARM: reduce "Booted secondary processor" message to debug level Drop the "CPUn: Booted secondary processor" message from info to debug level. We later print how many CPUs came online, so listing each one is redundant, and when using hotplug, can be quite noisy. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 3138d8ea9e55..7b18a1be179c 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -351,7 +351,7 @@ asmlinkage void secondary_start_kernel(void) cpu_init(); - pr_info("CPU%u: Booted secondary processor\n", cpu); + pr_debug("CPU%u: Booted secondary processor\n", cpu); preempt_disable(); trace_hardirqs_off(); From 1381c5a65fc6abc8b22f179da6a6577b0deb0687 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 12:13:59 +0000 Subject: [PATCH 31/62] ARM: remove "SMP: Total of %d processors activated." message The "SMP: Total of %d processors activated." message which we print in smp_cpus_done() provides no further information than the message in genreic code in smp_announce(). Kill it. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/smp.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 7b18a1be179c..5e6052e18850 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -387,9 +387,6 @@ asmlinkage void secondary_start_kernel(void) void __init smp_cpus_done(unsigned int max_cpus) { - pr_info("SMP: Total of %d processors activated.\n", - num_online_cpus()); - hyp_mode_check(); } From 719c9d1489bad6ff26fa1f6a7e3f760935663398 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 12:40:26 +0000 Subject: [PATCH 32/62] ARM: add machine name to stack dump output The generic dump_stack() code provides the facility to include the machine name in the stack dump, which can be useful information. Add a call to dump_stack_set_arch_desc() for the generic code to print this information. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/setup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index c03106378b49..8361652b6dab 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -900,6 +900,7 @@ void __init setup_arch(char **cmdline_p) mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type); machine_desc = mdesc; machine_name = mdesc->name; + dump_stack_set_arch_desc("%s", mdesc->name); if (mdesc->reboot_mode != REBOOT_HARD) reboot_mode = mdesc->reboot_mode; From 82112379b73c937576f40c99b4d93162343af6f9 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 13:26:48 +0000 Subject: [PATCH 33/62] ARM: move ftrace assembly code to separate file The ftrace assembly code doesn't need to live in entry-common.S and be surrounded with #ifdef CONFIG_FUNCTION_TRACER. Instead, move it to its own file and conditionally assemble it. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/Makefile | 1 + arch/arm/kernel/entry-common.S | 235 ------------------------------- arch/arm/kernel/entry-ftrace.S | 243 +++++++++++++++++++++++++++++++++ 3 files changed, 244 insertions(+), 235 deletions(-) create mode 100644 arch/arm/kernel/entry-ftrace.S diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 38ddd9f83d0e..738ebe5a91e6 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -47,6 +47,7 @@ endif obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o obj-$(CONFIG_ARM_ARCH_TIMER) += arch_timer.o +obj-$(CONFIG_FUNCTION_TRACER) += entry-ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 6bb09d4abdea..f8ccc21fa032 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -109,241 +109,6 @@ ENDPROC(ret_from_fork) #undef CALL #define CALL(x) .long x -#ifdef CONFIG_FUNCTION_TRACER -/* - * When compiling with -pg, gcc inserts a call to the mcount routine at the - * start of every function. In mcount, apart from the function's address (in - * lr), we need to get hold of the function's caller's address. - * - * Older GCCs (pre-4.4) inserted a call to a routine called mcount like this: - * - * bl mcount - * - * These versions have the limitation that in order for the mcount routine to - * be able to determine the function's caller's address, an APCS-style frame - * pointer (which is set up with something like the code below) is required. - * - * mov ip, sp - * push {fp, ip, lr, pc} - * sub fp, ip, #4 - * - * With EABI, these frame pointers are not available unless -mapcs-frame is - * specified, and if building as Thumb-2, not even then. - * - * Newer GCCs (4.4+) solve this problem by introducing a new version of mcount, - * with call sites like: - * - * push {lr} - * bl __gnu_mcount_nc - * - * With these compilers, frame pointers are not necessary. - * - * mcount can be thought of as a function called in the middle of a subroutine - * call. As such, it needs to be transparent for both the caller and the - * callee: the original lr needs to be restored when leaving mcount, and no - * registers should be clobbered. (In the __gnu_mcount_nc implementation, we - * clobber the ip register. This is OK because the ARM calling convention - * allows it to be clobbered in subroutines and doesn't use it to hold - * parameters.) - * - * When using dynamic ftrace, we patch out the mcount call by a "mov r0, r0" - * for the mcount case, and a "pop {lr}" for the __gnu_mcount_nc case (see - * arch/arm/kernel/ftrace.c). - */ - -#ifndef CONFIG_OLD_MCOUNT -#if (__GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 4)) -#error Ftrace requires CONFIG_FRAME_POINTER=y with GCC older than 4.4.0. -#endif -#endif - -.macro mcount_adjust_addr rd, rn - bic \rd, \rn, #1 @ clear the Thumb bit if present - sub \rd, \rd, #MCOUNT_INSN_SIZE -.endm - -.macro __mcount suffix - mcount_enter - ldr r0, =ftrace_trace_function - ldr r2, [r0] - adr r0, .Lftrace_stub - cmp r0, r2 - bne 1f - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ldr r1, =ftrace_graph_return - ldr r2, [r1] - cmp r0, r2 - bne ftrace_graph_caller\suffix - - ldr r1, =ftrace_graph_entry - ldr r2, [r1] - ldr r0, =ftrace_graph_entry_stub - cmp r0, r2 - bne ftrace_graph_caller\suffix -#endif - - mcount_exit - -1: mcount_get_lr r1 @ lr of instrumented func - mcount_adjust_addr r0, lr @ instrumented function - adr lr, BSYM(2f) - mov pc, r2 -2: mcount_exit -.endm - -.macro __ftrace_caller suffix - mcount_enter - - mcount_get_lr r1 @ lr of instrumented func - mcount_adjust_addr r0, lr @ instrumented function - - .globl ftrace_call\suffix -ftrace_call\suffix: - bl ftrace_stub - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - .globl ftrace_graph_call\suffix -ftrace_graph_call\suffix: - mov r0, r0 -#endif - - mcount_exit -.endm - -.macro __ftrace_graph_caller - sub r0, fp, #4 @ &lr of instrumented routine (&parent) -#ifdef CONFIG_DYNAMIC_FTRACE - @ called from __ftrace_caller, saved in mcount_enter - ldr r1, [sp, #16] @ instrumented routine (func) - mcount_adjust_addr r1, r1 -#else - @ called from __mcount, untouched in lr - mcount_adjust_addr r1, lr @ instrumented routine (func) -#endif - mov r2, fp @ frame pointer - bl prepare_ftrace_return - mcount_exit -.endm - -#ifdef CONFIG_OLD_MCOUNT -/* - * mcount - */ - -.macro mcount_enter - stmdb sp!, {r0-r3, lr} -.endm - -.macro mcount_get_lr reg - ldr \reg, [fp, #-4] -.endm - -.macro mcount_exit - ldr lr, [fp, #-4] - ldmia sp!, {r0-r3, pc} -.endm - -ENTRY(mcount) -#ifdef CONFIG_DYNAMIC_FTRACE - stmdb sp!, {lr} - ldr lr, [fp, #-4] - ldmia sp!, {pc} -#else - __mcount _old -#endif -ENDPROC(mcount) - -#ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(ftrace_caller_old) - __ftrace_caller _old -ENDPROC(ftrace_caller_old) -#endif - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller_old) - __ftrace_graph_caller -ENDPROC(ftrace_graph_caller_old) -#endif - -.purgem mcount_enter -.purgem mcount_get_lr -.purgem mcount_exit -#endif - -/* - * __gnu_mcount_nc - */ - -.macro mcount_enter -/* - * This pad compensates for the push {lr} at the call site. Note that we are - * unable to unwind through a function which does not otherwise save its lr. - */ - UNWIND(.pad #4) - stmdb sp!, {r0-r3, lr} - UNWIND(.save {r0-r3, lr}) -.endm - -.macro mcount_get_lr reg - ldr \reg, [sp, #20] -.endm - -.macro mcount_exit - ldmia sp!, {r0-r3, ip, lr} - ret ip -.endm - -ENTRY(__gnu_mcount_nc) -UNWIND(.fnstart) -#ifdef CONFIG_DYNAMIC_FTRACE - mov ip, lr - ldmia sp!, {lr} - ret ip -#else - __mcount -#endif -UNWIND(.fnend) -ENDPROC(__gnu_mcount_nc) - -#ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(ftrace_caller) -UNWIND(.fnstart) - __ftrace_caller -UNWIND(.fnend) -ENDPROC(ftrace_caller) -#endif - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) -UNWIND(.fnstart) - __ftrace_graph_caller -UNWIND(.fnend) -ENDPROC(ftrace_graph_caller) -#endif - -.purgem mcount_enter -.purgem mcount_get_lr -.purgem mcount_exit - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - .globl return_to_handler -return_to_handler: - stmdb sp!, {r0-r3} - mov r0, fp @ frame pointer - bl ftrace_return_to_handler - mov lr, r0 @ r0 has real ret addr - ldmia sp!, {r0-r3} - ret lr -#endif - -ENTRY(ftrace_stub) -.Lftrace_stub: - ret lr -ENDPROC(ftrace_stub) - -#endif /* CONFIG_FUNCTION_TRACER */ - /*============================================================================= * SWI handler *----------------------------------------------------------------------------- diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S new file mode 100644 index 000000000000..fe57c73e70a4 --- /dev/null +++ b/arch/arm/kernel/entry-ftrace.S @@ -0,0 +1,243 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include + +#include "entry-header.S" + +/* + * When compiling with -pg, gcc inserts a call to the mcount routine at the + * start of every function. In mcount, apart from the function's address (in + * lr), we need to get hold of the function's caller's address. + * + * Older GCCs (pre-4.4) inserted a call to a routine called mcount like this: + * + * bl mcount + * + * These versions have the limitation that in order for the mcount routine to + * be able to determine the function's caller's address, an APCS-style frame + * pointer (which is set up with something like the code below) is required. + * + * mov ip, sp + * push {fp, ip, lr, pc} + * sub fp, ip, #4 + * + * With EABI, these frame pointers are not available unless -mapcs-frame is + * specified, and if building as Thumb-2, not even then. + * + * Newer GCCs (4.4+) solve this problem by introducing a new version of mcount, + * with call sites like: + * + * push {lr} + * bl __gnu_mcount_nc + * + * With these compilers, frame pointers are not necessary. + * + * mcount can be thought of as a function called in the middle of a subroutine + * call. As such, it needs to be transparent for both the caller and the + * callee: the original lr needs to be restored when leaving mcount, and no + * registers should be clobbered. (In the __gnu_mcount_nc implementation, we + * clobber the ip register. This is OK because the ARM calling convention + * allows it to be clobbered in subroutines and doesn't use it to hold + * parameters.) + * + * When using dynamic ftrace, we patch out the mcount call by a "mov r0, r0" + * for the mcount case, and a "pop {lr}" for the __gnu_mcount_nc case (see + * arch/arm/kernel/ftrace.c). + */ + +#ifndef CONFIG_OLD_MCOUNT +#if (__GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 4)) +#error Ftrace requires CONFIG_FRAME_POINTER=y with GCC older than 4.4.0. +#endif +#endif + +.macro mcount_adjust_addr rd, rn + bic \rd, \rn, #1 @ clear the Thumb bit if present + sub \rd, \rd, #MCOUNT_INSN_SIZE +.endm + +.macro __mcount suffix + mcount_enter + ldr r0, =ftrace_trace_function + ldr r2, [r0] + adr r0, .Lftrace_stub + cmp r0, r2 + bne 1f + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + ldr r1, =ftrace_graph_return + ldr r2, [r1] + cmp r0, r2 + bne ftrace_graph_caller\suffix + + ldr r1, =ftrace_graph_entry + ldr r2, [r1] + ldr r0, =ftrace_graph_entry_stub + cmp r0, r2 + bne ftrace_graph_caller\suffix +#endif + + mcount_exit + +1: mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + adr lr, BSYM(2f) + mov pc, r2 +2: mcount_exit +.endm + +.macro __ftrace_caller suffix + mcount_enter + + mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + + .globl ftrace_call\suffix +ftrace_call\suffix: + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_call\suffix +ftrace_graph_call\suffix: + mov r0, r0 +#endif + + mcount_exit +.endm + +.macro __ftrace_graph_caller + sub r0, fp, #4 @ &lr of instrumented routine (&parent) +#ifdef CONFIG_DYNAMIC_FTRACE + @ called from __ftrace_caller, saved in mcount_enter + ldr r1, [sp, #16] @ instrumented routine (func) + mcount_adjust_addr r1, r1 +#else + @ called from __mcount, untouched in lr + mcount_adjust_addr r1, lr @ instrumented routine (func) +#endif + mov r2, fp @ frame pointer + bl prepare_ftrace_return + mcount_exit +.endm + +#ifdef CONFIG_OLD_MCOUNT +/* + * mcount + */ + +.macro mcount_enter + stmdb sp!, {r0-r3, lr} +.endm + +.macro mcount_get_lr reg + ldr \reg, [fp, #-4] +.endm + +.macro mcount_exit + ldr lr, [fp, #-4] + ldmia sp!, {r0-r3, pc} +.endm + +ENTRY(mcount) +#ifdef CONFIG_DYNAMIC_FTRACE + stmdb sp!, {lr} + ldr lr, [fp, #-4] + ldmia sp!, {pc} +#else + __mcount _old +#endif +ENDPROC(mcount) + +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(ftrace_caller_old) + __ftrace_caller _old +ENDPROC(ftrace_caller_old) +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller_old) + __ftrace_graph_caller +ENDPROC(ftrace_graph_caller_old) +#endif + +.purgem mcount_enter +.purgem mcount_get_lr +.purgem mcount_exit +#endif + +/* + * __gnu_mcount_nc + */ + +.macro mcount_enter +/* + * This pad compensates for the push {lr} at the call site. Note that we are + * unable to unwind through a function which does not otherwise save its lr. + */ + UNWIND(.pad #4) + stmdb sp!, {r0-r3, lr} + UNWIND(.save {r0-r3, lr}) +.endm + +.macro mcount_get_lr reg + ldr \reg, [sp, #20] +.endm + +.macro mcount_exit + ldmia sp!, {r0-r3, ip, lr} + ret ip +.endm + +ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) +#ifdef CONFIG_DYNAMIC_FTRACE + mov ip, lr + ldmia sp!, {lr} + ret ip +#else + __mcount +#endif +UNWIND(.fnend) +ENDPROC(__gnu_mcount_nc) + +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(ftrace_caller) +UNWIND(.fnstart) + __ftrace_caller +UNWIND(.fnend) +ENDPROC(ftrace_caller) +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) +UNWIND(.fnstart) + __ftrace_graph_caller +UNWIND(.fnend) +ENDPROC(ftrace_graph_caller) +#endif + +.purgem mcount_enter +.purgem mcount_get_lr +.purgem mcount_exit + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl return_to_handler +return_to_handler: + stmdb sp!, {r0-r3} + mov r0, fp @ frame pointer + bl ftrace_return_to_handler + mov lr, r0 @ r0 has real ret addr + ldmia sp!, {r0-r3} + ret lr +#endif + +ENTRY(ftrace_stub) +.Lftrace_stub: + ret lr +ENDPROC(ftrace_stub) From 296630c9c8c6ff5f116b417fafa6067d4c7a786e Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 Oct 2014 13:31:04 +0000 Subject: [PATCH 34/62] ARM: io.c: clean up EXPORT_SYMBOL()s Place EXPORT_SYMBOL()s after the function definition. Tested-by: Felipe Balbi Signed-off-by: Russell King --- arch/arm/kernel/io.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm/kernel/io.c b/arch/arm/kernel/io.c index 9203cf883330..eedefe050022 100644 --- a/arch/arm/kernel/io.c +++ b/arch/arm/kernel/io.c @@ -51,6 +51,7 @@ void _memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) from++; } } +EXPORT_SYMBOL(_memcpy_fromio); /* * Copy data from "real" memory space to IO memory space. @@ -66,6 +67,7 @@ void _memcpy_toio(volatile void __iomem *to, const void *from, size_t count) to++; } } +EXPORT_SYMBOL(_memcpy_toio); /* * "memset" on IO memory space. @@ -79,7 +81,4 @@ void _memset_io(volatile void __iomem *dst, int c, size_t count) dst++; } } - -EXPORT_SYMBOL(_memcpy_fromio); -EXPORT_SYMBOL(_memcpy_toio); EXPORT_SYMBOL(_memset_io); From 20cb6abfe0062693183eb2a85f7c73792e96407f Mon Sep 17 00:00:00 2001 From: Lin Yongting Date: Wed, 26 Nov 2014 14:33:49 +0100 Subject: [PATCH 35/62] ARM: 8223/1: Add unwinding support for __memzero function The __memzero function never had unwinding annotations added. Currently, when accessing invalid pointer by __memzero occurs the backtrace shown will stop at __memzero or some completely unrelated function. Add unwinding annotations in hopes of getting a more useful backtrace in following cases: 1. die on accessing invalid pointer by __memzero 2. kprobe trapped at any instruction within __memzero 3. interrupted at any instruction within __memzero Signed-off-by: Lin Yongting Signed-off-by: Russell King --- arch/arm/lib/memzero.S | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S index 385ccb306fa2..0eded952e089 100644 --- a/arch/arm/lib/memzero.S +++ b/arch/arm/lib/memzero.S @@ -9,6 +9,7 @@ */ #include #include +#include .text .align 5 @@ -18,6 +19,7 @@ * mis-aligned by, and r1 is the number of bytes. If r1 < 4, then we * don't bother; we use byte stores instead. */ +UNWIND( .fnstart ) 1: subs r1, r1, #4 @ 1 do we have enough blt 5f @ 1 bytes to align with? cmp r3, #2 @ 1 @@ -47,6 +49,9 @@ ENTRY(__memzero) * use the LR */ str lr, [sp, #-4]! @ 1 +UNWIND( .fnend ) +UNWIND( .fnstart ) +UNWIND( .save {lr} ) mov ip, r2 @ 1 mov lr, r2 @ 1 @@ -66,6 +71,7 @@ ENTRY(__memzero) tst r1, #16 @ 1 16 bytes or more? stmneia r0!, {r2, r3, ip, lr} @ 4 ldr lr, [sp], #4 @ 1 +UNWIND( .fnend ) #else @@ -75,6 +81,9 @@ ENTRY(__memzero) */ stmfd sp!, {r4-r7, lr} +UNWIND( .fnend ) +UNWIND( .fnstart ) +UNWIND( .save {r4-r7, lr} ) mov r4, r2 mov r5, r2 mov r6, r2 @@ -105,9 +114,11 @@ ENTRY(__memzero) tst r1, #16 stmneia r0!, {r4-r7} ldmfd sp!, {r4-r7, lr} +UNWIND( .fnend ) #endif +UNWIND( .fnstart ) 4: tst r1, #8 @ 1 8 bytes or more? stmneia r0!, {r2, r3} @ 2 tst r1, #4 @ 1 4 bytes or more? @@ -122,4 +133,5 @@ ENTRY(__memzero) tst r1, #1 @ 1 a byte left over strneb r2, [r0], #1 @ 1 ret lr @ 1 +UNWIND( .fnend ) ENDPROC(__memzero) From 207a6cb06990c298d0eac982e053d370e216d93d Mon Sep 17 00:00:00 2001 From: Lin Yongting Date: Wed, 26 Nov 2014 14:36:15 +0100 Subject: [PATCH 36/62] ARM: 8224/1: Add unwinding support for memmove function The memmove function never had unwinding annotations added. Currently, when accessing invalid pointer by memmove occurs the backtrace shown will stop at memmove or some completely unrelated function. Add unwinding annotations in hopes of getting a more useful backtrace in following cases: 1. die on accessing invalid pointer by memmove 2. kprobe trapped at any instruction within memmove 3. interrupted at any instruction within memmove Signed-off-by: Lin Yongting Signed-off-by: Russell King --- arch/arm/lib/memmove.S | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S index d1fc0c0c342c..69a9d47fc5ab 100644 --- a/arch/arm/lib/memmove.S +++ b/arch/arm/lib/memmove.S @@ -12,6 +12,7 @@ #include #include +#include .text @@ -27,12 +28,17 @@ */ ENTRY(memmove) + UNWIND( .fnstart ) subs ip, r0, r1 cmphi r2, ip bls memcpy stmfd sp!, {r0, r4, lr} + UNWIND( .fnend ) + + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) @ in first stmfd block add r1, r1, r2 add r0, r0, r2 subs r2, r2, #4 @@ -45,6 +51,11 @@ ENTRY(memmove) 1: subs r2, r2, #(28) stmfd sp!, {r5 - r8} + UNWIND( .fnend ) + + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) + UNWIND( .save {r5 - r8} ) @ in second stmfd block blt 5f CALGN( ands ip, r0, #31 ) @@ -97,6 +108,10 @@ ENTRY(memmove) CALGN( bcs 2b ) 7: ldmfd sp!, {r5 - r8} + UNWIND( .fnend ) @ end of second stmfd block + + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block 8: movs r2, r2, lsl #31 ldrneb r3, [r1, #-1]! @@ -124,10 +139,13 @@ ENTRY(memmove) ldr r3, [r1, #0] beq 17f blt 18f + UNWIND( .fnend ) .macro backward_copy_shift push pull + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block subs r2, r2, #28 blt 14f @@ -137,6 +155,11 @@ ENTRY(memmove) CALGN( bcc 15f ) 11: stmfd sp!, {r5 - r9} + UNWIND( .fnend ) + + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) + UNWIND( .save {r5 - r9} ) @ in new second stmfd block PLD( pld [r1, #-4] ) PLD( subs r2, r2, #96 ) @@ -171,6 +194,10 @@ ENTRY(memmove) PLD( bge 13b ) ldmfd sp!, {r5 - r9} + UNWIND( .fnend ) @ end of the second stmfd block + + UNWIND( .fnstart ) + UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block 14: ands ip, r2, #28 beq 16f @@ -186,6 +213,7 @@ ENTRY(memmove) 16: add r1, r1, #(\pull / 8) b 8b + UNWIND( .fnend ) .endm From 279f487e0b471577e2b3c134e2ff9af939129d0f Mon Sep 17 00:00:00 2001 From: Lin Yongting Date: Wed, 26 Nov 2014 14:38:33 +0100 Subject: [PATCH 37/62] ARM: 8225/1: Add unwinding support for memory copy functions The memory copy functions(memcpy, __copy_from_user, __copy_to_user) never had unwinding annotations added. Currently, when accessing invalid pointer by these functions occurs the backtrace shown will stop at these functions or some completely unrelated function. Add unwinding annotations in hopes of getting a more useful backtrace in following cases: 1. die on accessing invalid pointer by these functions 2. kprobe trapped at any instruction within these functions 3. interrupted at any instruction within these functions Signed-off-by: Lin Yongting Signed-off-by: Russell King --- arch/arm/lib/copy_from_user.S | 5 +++++ arch/arm/lib/copy_template.S | 30 ++++++++++++++++++++++++++++++ arch/arm/lib/copy_to_user.S | 5 +++++ arch/arm/lib/memcpy.S | 5 +++++ 4 files changed, 45 insertions(+) diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 66a477a3e3cc..7a235b9952be 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -12,6 +12,7 @@ #include #include +#include /* * Prototype: @@ -77,6 +78,10 @@ stmdb sp!, {r0, r2, r3, \reg1, \reg2} .endm + .macro usave reg1 reg2 + UNWIND( .save {r0, r2, r3, \reg1, \reg2} ) + .endm + .macro exit reg1 reg2 add sp, sp, #8 ldmfd sp!, {r0, \reg1, \reg2} diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S index 3bc8eb811a73..652e4d98cd47 100644 --- a/arch/arm/lib/copy_template.S +++ b/arch/arm/lib/copy_template.S @@ -53,6 +53,12 @@ * data as needed by the implementation including this code. Called * upon code entry. * + * usave reg1 reg2 + * + * Unwind annotation macro is corresponding for 'enter' macro. + * It tell unwinder that preserved some provided registers on the stack + * and additional data by a prior 'enter' macro. + * * exit reg1 reg2 * * Restore registers with the values previously saved with the @@ -67,7 +73,12 @@ */ + UNWIND( .fnstart ) enter r4, lr + UNWIND( .fnend ) + + UNWIND( .fnstart ) + usave r4, lr @ in first stmdb block subs r2, r2, #4 blt 8f @@ -79,6 +90,11 @@ 1: subs r2, r2, #(28) stmfd sp!, {r5 - r8} + UNWIND( .fnend ) + + UNWIND( .fnstart ) + usave r4, lr + UNWIND( .save {r5 - r8} ) @ in second stmfd block blt 5f CALGN( ands ip, r0, #31 ) @@ -144,7 +160,10 @@ CALGN( bcs 2b ) 7: ldmfd sp!, {r5 - r8} + UNWIND( .fnend ) @ end of second stmfd block + UNWIND( .fnstart ) + usave r4, lr @ still in first stmdb block 8: movs r2, r2, lsl #31 ldr1b r1, r3, ne, abort=21f ldr1b r1, r4, cs, abort=21f @@ -173,10 +192,13 @@ ldr1w r1, lr, abort=21f beq 17f bgt 18f + UNWIND( .fnend ) .macro forward_copy_shift pull push + UNWIND( .fnstart ) + usave r4, lr @ still in first stmdb block subs r2, r2, #28 blt 14f @@ -187,7 +209,11 @@ CALGN( bcc 15f ) 11: stmfd sp!, {r5 - r9} + UNWIND( .fnend ) + UNWIND( .fnstart ) + usave r4, lr + UNWIND( .save {r5 - r9} ) @ in new second stmfd block PLD( pld [r1, #0] ) PLD( subs r2, r2, #96 ) PLD( pld [r1, #28] ) @@ -221,7 +247,10 @@ PLD( bge 13b ) ldmfd sp!, {r5 - r9} + UNWIND( .fnend ) @ end of the second stmfd block + UNWIND( .fnstart ) + usave r4, lr @ still in first stmdb block 14: ands ip, r2, #28 beq 16f @@ -236,6 +265,7 @@ 16: sub r1, r1, #(\push / 8) b 8b + UNWIND( .fnend ) .endm diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S index d066df686e17..a9d3db16ecb5 100644 --- a/arch/arm/lib/copy_to_user.S +++ b/arch/arm/lib/copy_to_user.S @@ -12,6 +12,7 @@ #include #include +#include /* * Prototype: @@ -80,6 +81,10 @@ stmdb sp!, {r0, r2, r3, \reg1, \reg2} .endm + .macro usave reg1 reg2 + UNWIND( .save {r0, r2, r3, \reg1, \reg2} ) + .endm + .macro exit reg1 reg2 add sp, sp, #8 ldmfd sp!, {r0, \reg1, \reg2} diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index a9b9e2287a09..7797e81e40e0 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -12,6 +12,7 @@ #include #include +#include #define LDR1W_SHIFT 0 #define STR1W_SHIFT 0 @@ -48,6 +49,10 @@ stmdb sp!, {r0, \reg1, \reg2} .endm + .macro usave reg1 reg2 + UNWIND( .save {r0, \reg1, \reg2} ) + .endm + .macro exit reg1 reg2 ldmfd sp!, {r0, \reg1, \reg2} .endm From b816ccc5c01fb7fe1fb001ff7aa5aa7e5a8aa76b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 18 Nov 2014 12:17:56 +0100 Subject: [PATCH 38/62] ARM: 8206/1: dmaengine: pl330: Add PM sleep support Add system suspend/resume capabilities to the pl330 driver so the amba bus clock could be also unprepared to conserve energy. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Russell King --- drivers/dma/pl330.c | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 39ea8d436b81..2d324f780719 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2627,6 +2627,46 @@ static int pl330_dma_device_slave_caps(struct dma_chan *dchan, return 0; } +/* + * Runtime PM callbacks are provided by amba/bus.c driver. + * + * It is assumed here that IRQ safe runtime PM is chosen in probe and amba + * bus driver will only disable/enable the clock in runtime PM callbacks. + */ +static int __maybe_unused pl330_suspend(struct device *dev) +{ + struct amba_device *pcdev = to_amba_device(dev); + + pm_runtime_disable(dev); + + if (!pm_runtime_status_suspended(dev)) { + /* amba did not disable the clock */ + amba_pclk_disable(pcdev); + } + amba_pclk_unprepare(pcdev); + + return 0; +} + +static int __maybe_unused pl330_resume(struct device *dev) +{ + struct amba_device *pcdev = to_amba_device(dev); + int ret; + + ret = amba_pclk_prepare(pcdev); + if (ret) + return ret; + + if (!pm_runtime_status_suspended(dev)) + ret = amba_pclk_enable(pcdev); + + pm_runtime_enable(dev); + + return ret; +} + +static SIMPLE_DEV_PM_OPS(pl330_pm, pl330_suspend, pl330_resume); + static int pl330_probe(struct amba_device *adev, const struct amba_id *id) { @@ -2852,6 +2892,7 @@ static struct amba_driver pl330_driver = { .drv = { .owner = THIS_MODULE, .name = "dma-pl330", + .pm = &pl330_pm, }, .id_table = pl330_ids, .probe = pl330_probe, From 119acbd24c54d73c8941f43f16817c3417237413 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Fri, 21 Nov 2014 16:26:29 +0100 Subject: [PATCH 39/62] ARM: 8217/1: sa1100 collie: use gpio-charger instead of pda-power Use gpio-charger driver instead of pda-power: it automatically cares about used gpio and since collie does not differentiate between usb and ac chargers, pda-power is an overkill for it. As a bonus this allows us to remove gpio_to_irq calls from machine init call - it is fragile. These gpio_to_irq calls will fail if gpios are registered later, via device driver mechanisms. Signed-off-by: Dmitry Eremin-Solenikov Signed-off-by: Russell King --- arch/arm/mach-sa1100/collie.c | 55 +++++------------------------------ 1 file changed, 7 insertions(+), 48 deletions(-) diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c index 108939f8d053..b90c7d828391 100644 --- a/arch/arm/mach-sa1100/collie.c +++ b/arch/arm/mach-sa1100/collie.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include