From d0d62230185e9d1a683bfa5cdfe5e520577f68d1 Mon Sep 17 00:00:00 2001 From: Pratyush Anand Date: Fri, 13 Feb 2015 04:06:21 +0000 Subject: arm64: ftrace: fix ftrace_modify_graph_caller for branch replace ftrace_enable_ftrace_graph_caller and ftrace_disable_ftrace_graph_caller should replace B(jmp) instruction and not BL(call) instruction. Commit 9f1ae7596aad("arm64: Correct ftrace calls to aarch64_insn_gen_branch_imm()") had a typo and used AARCH64_INSN_BRANCH_LINK instead of AARCH64_INSN_BRANCH_NOLINK. Either instruction will work, as the link register is saved/restored across the branch but this better matches the intention of the code. Signed-off-by: Pratyush Anand Signed-off-by: Will Deacon --- arch/arm64/kernel/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index cf8556ae09d0..c851be795080 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -156,7 +156,7 @@ static int ftrace_modify_graph_caller(bool enable) branch = aarch64_insn_gen_branch_imm(pc, (unsigned long)ftrace_graph_caller, - AARCH64_INSN_BRANCH_LINK); + AARCH64_INSN_BRANCH_NOLINK); nop = aarch64_insn_gen_nop(); if (enable) -- cgit v1.2.3 From 115386f89b5415fcdf641faad0d459cd5c07d225 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 18 Feb 2015 15:40:17 +0000 Subject: arm64: insn: fix compare-and-branch encodings Fix cbz/cbnz having the mask offset by a bit, and add encodings for tbz/tbnz so that all branch forms are represented. Signed-off-by: Robin Murphy Acked-by: Will Deacon Acked-by: Zi Shen Lim Signed-off-by: Will Deacon --- arch/arm64/include/asm/insn.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index e2ff32a93b5c..d2f49423c5dc 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -264,8 +264,10 @@ __AARCH64_INSN_FUNCS(ands, 0x7F200000, 0x6A000000) __AARCH64_INSN_FUNCS(bics, 0x7F200000, 0x6A200000) __AARCH64_INSN_FUNCS(b, 0xFC000000, 0x14000000) __AARCH64_INSN_FUNCS(bl, 0xFC000000, 0x94000000) -__AARCH64_INSN_FUNCS(cbz, 0xFE000000, 0x34000000) -__AARCH64_INSN_FUNCS(cbnz, 0xFE000000, 0x35000000) +__AARCH64_INSN_FUNCS(cbz, 0x7F000000, 0x34000000) +__AARCH64_INSN_FUNCS(cbnz, 0x7F000000, 0x35000000) +__AARCH64_INSN_FUNCS(tbz, 0x7F000000, 0x36000000) +__AARCH64_INSN_FUNCS(tbnz, 0x7F000000, 0x37000000) __AARCH64_INSN_FUNCS(bcond, 0xFF000010, 0x54000000) __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) -- cgit v1.2.3 From f3e39273e0a9a5c9dc78cd667ec3663e97e0e989 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 20 Feb 2015 13:53:13 +0000 Subject: arm64: guard asm/assembler.h against multiple inclusions asm/assembler.h lacks the usual guard against multiple inclusion, leading to a compilation failure if it is accidentally included twice. Using the classic #ifndef/#define/#endif construct solves the issue. Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- arch/arm64/include/asm/assembler.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 5901480bfdca..750bac4e637e 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -20,6 +20,9 @@ #error "Only include this from assembly code" #endif +#ifndef __ASM_ASSEMBLER_H +#define __ASM_ASSEMBLER_H + #include #include @@ -155,3 +158,5 @@ lr .req x30 // link register #endif orr \rd, \lbits, \hbits, lsl #32 .endm + +#endif /* __ASM_ASSEMBLER_H */ -- cgit v1.2.3 From e1b6b6ce55a0a25c8aa8af019095253b2133a41a Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Tue, 24 Feb 2015 17:21:07 -0600 Subject: arm64: vdso: minor ABI fix for clock_getres The vdso implementation of clock_getres currently returns 0 (success) whenever a null timespec is provided by the caller, regardless of the clock id supplied. This behavior is incorrect. It should fall back to syscall when an unrecognized clock id is passed, even when the timespec argument is null. This ensures that clock_getres always returns an error for invalid clock ids. Signed-off-by: Nathan Lynch Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/vdso/gettimeofday.S | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index fe652ffd34c2..efa79e8d4196 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -174,8 +174,6 @@ ENDPROC(__kernel_clock_gettime) /* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */ ENTRY(__kernel_clock_getres) .cfi_startproc - cbz w1, 3f - cmp w0, #CLOCK_REALTIME ccmp w0, #CLOCK_MONOTONIC, #0x4, ne b.ne 1f @@ -188,6 +186,7 @@ ENTRY(__kernel_clock_getres) b.ne 4f ldr x2, 6f 2: + cbz w1, 3f stp xzr, x2, [x1] 3: /* res == NULL. */ -- cgit v1.2.3 From f5e0a12ca2d939e47995f73428d9bf1ad372b289 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 25 Feb 2015 12:10:35 +0000 Subject: arm64: psci: move psci firmware calls out of line An arm64 allmodconfig fails to build with GCC 5 due to __asmeq assertions in the PSCI firmware calling code firing due to mcount preambles breaking our assumptions about register allocation of function arguments: /tmp/ccDqJsJ6.s: Assembler messages: /tmp/ccDqJsJ6.s:60: Error: .err encountered /tmp/ccDqJsJ6.s:61: Error: .err encountered /tmp/ccDqJsJ6.s:62: Error: .err encountered /tmp/ccDqJsJ6.s:99: Error: .err encountered /tmp/ccDqJsJ6.s:100: Error: .err encountered /tmp/ccDqJsJ6.s:101: Error: .err encountered This patch fixes the issue by moving the PSCI calls out-of-line into their own assembly files, which are safe from the compiler's meddling fingers. Reported-by: Andy Whitcroft Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/Makefile | 5 +++-- arch/arm64/kernel/psci-call.S | 28 ++++++++++++++++++++++++++++ arch/arm64/kernel/psci.c | 37 +++---------------------------------- 3 files changed, 34 insertions(+), 36 deletions(-) create mode 100644 arch/arm64/kernel/psci-call.S diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index bef04afd6031..5ee07eee80c2 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -15,8 +15,9 @@ CFLAGS_REMOVE_return_address.o = -pg arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o return_address.o \ - cpuinfo.o cpu_errata.o alternative.o cacheinfo.o + hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o \ + return_address.o cpuinfo.o cpu_errata.o \ + alternative.o cacheinfo.o arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o entry32.o \ diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S new file mode 100644 index 000000000000..cf83e61cd3b5 --- /dev/null +++ b/arch/arm64/kernel/psci-call.S @@ -0,0 +1,28 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2015 ARM Limited + * + * Author: Will Deacon + */ + +#include + +/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ +ENTRY(__invoke_psci_fn_hvc) + hvc #0 + ret +ENDPROC(__invoke_psci_fn_hvc) + +/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ +ENTRY(__invoke_psci_fn_smc) + smc #0 + ret +ENDPROC(__invoke_psci_fn_smc) diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 3425f311c49e..9b8a70ae64a1 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -57,6 +57,9 @@ static struct psci_operations psci_ops; static int (*invoke_psci_fn)(u64, u64, u64, u64); typedef int (*psci_initcall_t)(const struct device_node *); +asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64); +asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64); + enum psci_function { PSCI_FN_CPU_SUSPEND, PSCI_FN_CPU_ON, @@ -109,40 +112,6 @@ static void psci_power_state_unpack(u32 power_state, PSCI_0_2_POWER_STATE_AFFL_SHIFT; } -/* - * The following two functions are invoked via the invoke_psci_fn pointer - * and will not be inlined, allowing us to piggyback on the AAPCS. - */ -static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, - u64 arg2) -{ - asm volatile( - __asmeq("%0", "x0") - __asmeq("%1", "x1") - __asmeq("%2", "x2") - __asmeq("%3", "x3") - "hvc #0\n" - : "+r" (function_id) - : "r" (arg0), "r" (arg1), "r" (arg2)); - - return function_id; -} - -static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, - u64 arg2) -{ - asm volatile( - __asmeq("%0", "x0") - __asmeq("%1", "x1") - __asmeq("%2", "x2") - __asmeq("%3", "x3") - "smc #0\n" - : "+r" (function_id) - : "r" (arg0), "r" (arg1), "r" (arg2)); - - return function_id; -} - static int psci_get_version(void) { int err; -- cgit v1.2.3 From 06ff87bae8d30ab9c949ae8729355323e18107b4 Mon Sep 17 00:00:00 2001 From: Yingjoe Chen Date: Wed, 25 Feb 2015 10:47:45 +0800 Subject: arm64: mm: remove unused functions and variable protoypes The functions __cpu_flush_user_tlb_range and __cpu_flush_kern_tlb_range were removed in commit fa48e6f780 'arm64: mm: Optimise tlb flush logic where we have >4K granule'. Global variable cpu_tlb was never used in arm64. Remove them. Signed-off-by: Yingjoe Chen Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/tlbflush.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 73f0ce570fb3..4abe9b945f77 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -24,11 +24,6 @@ #include #include -extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *); -extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long); - -extern struct cpu_tlb_fns cpu_tlb; - /* * TLB Management * ============== -- cgit v1.2.3 From 6910fa16dbe142f6a0fd0fd7c249f9883ff7fc8a Mon Sep 17 00:00:00 2001 From: Feng Kan Date: Tue, 24 Feb 2015 15:40:21 -0800 Subject: arm64: enable PTE type bit in the mask for pte_modify Caught during Trinity testing. The pte_modify does not allow modification for PTE type bit. This cause the test to hang the system. It is found that the PTE can't transit from an inaccessible page (b00) to a valid page (b11) because the mask does not allow it. This happens when a big block of mmaped memory is set the PROT_NONE, then the a small piece is broken off and set to PROT_WRITE | PROT_READ cause a huge page split. Signed-off-by: Feng Kan Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 16449c535e50..800ec0e87ed9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -460,7 +460,7 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID | PTE_WRITE; + PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } -- cgit v1.2.3 From 0eee0fbd41c7b57d01136df2519c92ec1506e333 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 19 Feb 2015 17:25:16 +0000 Subject: arm64: crypto: increase AES interleave to 4x This patch increases the interleave factor for parallel AES modes to 4x. This improves performance on Cortex-A57 by ~35%. This is due to the 3-cycle latency of AES instructions on the A57's relatively deep pipeline (compared to Cortex-A53 where the AES instruction latency is only 2 cycles). At the same time, disable inline expansion of the core AES functions, as the performance benefit of this feature is negligible. Measured on AMD Seattle (using tcrypt.ko mode=500 sec=1): Baseline (2x interleave, inline expansion) ------------------------------------------ testing speed of async cbc(aes) (cbc-aes-ce) decryption test 4 (128 bit key, 8192 byte blocks): 95545 operations in 1 seconds test 14 (256 bit key, 8192 byte blocks): 68496 operations in 1 seconds This patch (4x interleave, no inline expansion) ----------------------------------------------- testing speed of async cbc(aes) (cbc-aes-ce) decryption test 4 (128 bit key, 8192 byte blocks): 124735 operations in 1 seconds test 14 (256 bit key, 8192 byte blocks): 92328 operations in 1 seconds Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/crypto/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index 5720608c50b1..abb79b3cfcfe 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -29,7 +29,7 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o aes-neon-blk-y := aes-glue-neon.o aes-neon.o -AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE +AFLAGS_aes-ce.o := -DINTERLEAVE=4 AFLAGS_aes-neon.o := -DINTERLEAVE=4 CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS -- cgit v1.2.3 From f6242cac10427c546271050b31c891a078e490cd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Feb 2015 16:30:21 +0000 Subject: arm64: Fix text patching logic when using fixmap Patch 2f896d586610 ("arm64: use fixmap for text patching") changed the way we patch the kernel text, using a fixmap when the kernel or modules are flagged as read only. Unfortunately, a flaw in the logic makes it fall over when patching modules without CONFIG_DEBUG_SET_MODULE_RONX enabled: [...] [ 32.032636] Call trace: [ 32.032716] [] __copy_to_user+0x2c/0x60 [ 32.032837] [] __aarch64_insn_write+0x94/0xf8 [ 32.033027] [] aarch64_insn_patch_text_nosync+0x18/0x58 [ 32.033200] [] ftrace_modify_code+0x58/0x84 [ 32.033363] [] ftrace_make_nop+0x3c/0x58 [ 32.033532] [] ftrace_process_locs+0x3d0/0x5c8 [ 32.033709] [] ftrace_module_init+0x28/0x34 [ 32.033882] [] load_module+0xbb8/0xfc4 [ 32.034044] [] SyS_finit_module+0x94/0xc4 [...] This is triggered by the use of virt_to_page() on a module address, which ends to pointing to Nowhereland if you're lucky, or corrupt your precious data if not. This patch fixes the logic by mimicking what is done on arm: - If we're patching a module and CONFIG_DEBUG_SET_MODULE_RONX is set, use vmalloc_to_page(). - If we're patching the kernel and CONFIG_DEBUG_RODATA is set, use virt_to_page(). - Otherwise, use the provided address, as we can write to it directly. Tested on 4.0-rc1 as a KVM guest. Reported-by: Richard W.M. Jones Reviewed-by: Kees Cook Acked-by: Mark Rutland Acked-by: Laura Abbott Tested-by: Richard W.M. Jones Cc: Will Deacon Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/kernel/insn.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 27d4864577e5..c8eca88f12e6 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -87,8 +87,10 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX)) page = vmalloc_to_page(addr); - else + else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA)) page = virt_to_page(addr); + else + return addr; BUG_ON(!page); set_fixmap(fixmap, page_to_phys(page)); -- cgit v1.2.3 From a1e50a82256ed2f1312e70c52a84323e2e378f49 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 5 Feb 2015 18:01:53 +0000 Subject: arm64: Increase the swiotlb buffer size 64MB With commit 3690951fc6d4 (arm64: Use swiotlb late initialisation), the swiotlb buffer size is limited to MAX_ORDER_NR_PAGES. However, there are platforms with 32-bit only devices that require bounce buffering via swiotlb. This patch changes the swiotlb initialisation to an early 64MB memblock allocation. In order to get the swiotlb buffer correctly allocated (via memblock_virt_alloc_low_nopanic), this patch also defines ARCH_LOW_ADDRESS_LIMIT to the maximum physical address capable of 32-bit DMA. Reported-by: Kefeng Wang Tested-by: Kefeng Wang Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/processor.h | 3 ++- arch/arm64/mm/dma-mapping.c | 16 +++------------- arch/arm64/mm/init.c | 14 +++++++++----- 3 files changed, 14 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index f9be30ea1cbd..20e9591a60cf 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -45,7 +45,8 @@ #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ -#define ARCH_LOW_ADDRESS_LIMIT PHYS_MASK +extern phys_addr_t arm64_dma_phys_limit; +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) #endif /* __KERNEL__ */ struct debug_info { diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 0a24b9b8c698..58e0c2bdde04 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -348,8 +348,6 @@ static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, }; -extern int swiotlb_late_init_with_default_size(size_t default_size); - static int __init atomic_pool_init(void) { pgprot_t prot = __pgprot(PROT_NORMAL_NC); @@ -411,21 +409,13 @@ out: return -ENOMEM; } -static int __init swiotlb_late_init(void) +static int __init arm64_dma_init(void) { - size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); + int ret; dma_ops = &swiotlb_dma_ops; - return swiotlb_late_init_with_default_size(swiotlb_size); -} - -static int __init arm64_dma_init(void) -{ - int ret = 0; - - ret |= swiotlb_late_init(); - ret |= atomic_pool_init(); + ret = atomic_pool_init(); return ret; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 71145f952070..ae85da6307bb 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -45,6 +46,7 @@ #include "mm.h" phys_addr_t memstart_addr __read_mostly = 0; +phys_addr_t arm64_dma_phys_limit __read_mostly; #ifdef CONFIG_BLK_DEV_INITRD static int __init early_initrd(char *p) @@ -85,7 +87,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) { - max_dma = PFN_DOWN(max_zone_dma_phys()); + max_dma = PFN_DOWN(arm64_dma_phys_limit); zone_size[ZONE_DMA] = max_dma - min; } zone_size[ZONE_NORMAL] = max - max_dma; @@ -156,8 +158,6 @@ early_param("mem", early_mem); void __init arm64_memblock_init(void) { - phys_addr_t dma_phys_limit = 0; - memblock_enforce_memory_limit(memory_limit); /* @@ -174,8 +174,10 @@ void __init arm64_memblock_init(void) /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) - dma_phys_limit = max_zone_dma_phys(); - dma_contiguous_reserve(dma_phys_limit); + arm64_dma_phys_limit = max_zone_dma_phys(); + else + arm64_dma_phys_limit = PHYS_MASK + 1; + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); memblock_dump_all(); @@ -276,6 +278,8 @@ static void __init free_unused_memmap(void) */ void __init mem_init(void) { + swiotlb_init(1); + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); #ifndef CONFIG_SPARSEMEM_VMEMMAP -- cgit v1.2.3 From 9d42d48a342aee208c1154696196497fdc556bbf Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 23 Feb 2015 15:13:40 +0000 Subject: arm64: compat Fix siginfo_t -> compat_siginfo_t conversion on big endian The native (64-bit) sigval_t union contains sival_int (32-bit) and sival_ptr (64-bit). When a compat application invokes a syscall that takes a sigval_t value (as part of a larger structure, e.g. compat_sys_mq_notify, compat_sys_timer_create), the compat_sigval_t union is converted to the native sigval_t with sival_int overlapping with either the least or the most significant half of sival_ptr, depending on endianness. When the corresponding signal is delivered to a compat application, on big endian the current (compat_uptr_t)sival_ptr cast always returns 0 since sival_int corresponds to the top part of sival_ptr. This patch fixes copy_siginfo_to_user32() so that sival_int is copied to the compat_siginfo_t structure. Cc: Reported-by: Bamvor Jian Zhang Tested-by: Bamvor Jian Zhang Signed-off-by: Catalin Marinas --- arch/arm64/kernel/signal32.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index c20a300e2213..d26fcd4cd6e6 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -154,8 +154,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_TIMER: err |= __put_user(from->si_tid, &to->si_tid); err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, - &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_POLL: err |= __put_user(from->si_band, &to->si_band); @@ -184,7 +183,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_MESGQ: /* But this is */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_SYS: err |= __put_user((compat_uptr_t)(unsigned long) -- cgit v1.2.3 From af4819af8db05da4753b3b74a11cb00b381247e7 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 27 Feb 2015 17:54:31 +0000 Subject: arm64: cpuidle: add asm/proc-fns.h inclusion ARM64 CPUidle driver requires the cpu_do_idle function so that it can be used to enter the shallowest idle state, and it is declared in asm/proc-fns.h. The current ARM64 CPUidle driver does not include asm/proc-fns.h explicitly and it has so far relied on implicit inclusion from other header files. Owing to some header dependencies reshuffling this currently triggers build failures when CONFIG_ARM64_64K_PAGES=y: drivers/cpuidle/cpuidle-arm64.c: In function "arm64_enter_idle_state" drivers/cpuidle/cpuidle-arm64.c:42:3: error: implicit declaration of function "cpu_do_idle" [-Werror=implicit-function-declaration] cpu_do_idle(); ^ This patch adds the explicit inclusion of the asm/proc-fns.h header file in the arm64 asm/cpuidle.h header file, so that the build breakage is fixed and the required header inclusion is added to the appropriate arch back-end CPUidle header, already included by the CPUidle arm64 driver, where CPUidle arch related function declarations belong. Reported-by: Laura Abbott Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Tested-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h index 0710654631e7..c60643f14cda 100644 --- a/arch/arm64/include/asm/cpuidle.h +++ b/arch/arm64/include/asm/cpuidle.h @@ -1,6 +1,8 @@ #ifndef __ASM_CPUIDLE_H #define __ASM_CPUIDLE_H +#include + #ifdef CONFIG_CPU_IDLE extern int cpu_init_idle(unsigned int cpu); extern int cpu_suspend(unsigned long arg); -- cgit v1.2.3