From 5e6dca82bcaa49348f9e5fcb48df4881f6d6c4ae Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 12 Jan 2021 11:46:24 -0800 Subject: x86/entry: Emit a symbol for register restoring thunk Arnd found a randconfig that produces the warning: arch/x86/entry/thunk_64.o: warning: objtool: missing symbol for insn at offset 0x3e when building with LLVM_IAS=1 (Clang's integrated assembler). Josh notes: With the LLVM assembler not generating section symbols, objtool has no way to reference this code when it generates ORC unwinder entries, because this code is outside of any ELF function. The limitation now being imposed by objtool is that all code must be contained in an ELF symbol. And .L symbols don't create such symbols. So basically, you can use an .L symbol *inside* a function or a code segment, you just can't use the .L symbol to contain the code using a SYM_*_START/END annotation pair. Fangrui notes that this optimization is helpful for reducing image size when compiling with -ffunction-sections and -fdata-sections. I have observed on the order of tens of thousands of symbols for the kernel images built with those flags. A patch has been authored against GNU binutils to match this behavior of not generating unused section symbols ([1]), so this will also become a problem for users of GNU binutils once they upgrade to 2.36. Omit the .L prefix on a label so that the assembler will emit an entry into the symbol table for the label, with STB_LOCAL binding. This enables objtool to generate proper unwind info here with LLVM_IAS=1 or GNU binutils 2.36+. [ bp: Massage commit message. ] Reported-by: Arnd Bergmann Suggested-by: Josh Poimboeuf Suggested-by: Borislav Petkov Suggested-by: Mark Brown Signed-off-by: Nick Desaulniers Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20210112194625.4181814-1-ndesaulniers@google.com Link: https://github.com/ClangBuiltLinux/linux/issues/1209 Link: https://reviews.llvm.org/D93783 Link: https://sourceware.org/binutils/docs/as/Symbol-Names.html Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1408485ce69f844dcd7ded093a8 [1] --- arch/x86/entry/thunk_64.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index ccd32877a3c4..c9a9fbf1655f 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -31,7 +31,7 @@ SYM_FUNC_START_NOALIGN(\name) .endif call \func - jmp .L_restore + jmp __thunk_restore SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -44,7 +44,7 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION -SYM_CODE_START_LOCAL_NOALIGN(.L_restore) +SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %r11 popq %r10 popq %r9 @@ -56,6 +56,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %rdi popq %rbp ret - _ASM_NOKPROBE(.L_restore) -SYM_CODE_END(.L_restore) + _ASM_NOKPROBE(__thunk_restore) +SYM_CODE_END(__thunk_restore) #endif -- cgit v1.2.3 From 0bab9cb2d980d7c075cffb9216155f7835237f98 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 14 Jan 2021 14:25:35 +0100 Subject: x86/entry: Remove put_ret_addr_in_rdi THUNK macro argument That logic is unused since 320100a5ffe5 ("x86/entry: Remove the TRACE_IRQS cruft") Remove it. Suggested-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/YAAszZJ2GcIYZmB5@hirez.programming.kicks-ass.net --- arch/x86/entry/thunk_64.S | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index c9a9fbf1655f..496b11ec469d 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -10,7 +10,7 @@ #include /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func, put_ret_addr_in_rdi=0 + .macro THUNK name, func SYM_FUNC_START_NOALIGN(\name) pushq %rbp movq %rsp, %rbp @@ -25,11 +25,6 @@ SYM_FUNC_START_NOALIGN(\name) pushq %r10 pushq %r11 - .if \put_ret_addr_in_rdi - /* 8(%rbp) is return addr on stack */ - movq 8(%rbp), %rdi - .endif - call \func jmp __thunk_restore SYM_FUNC_END(\name) -- cgit v1.2.3 From 336e8eb2a3cfe2285c314cd85630076da365f6c6 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 21 Jan 2021 14:31:17 +0800 Subject: riscv: Fixup pfn_valid error with wrong max_mapnr The max_mapnr is the number of PFNs, not absolute PFN offset. Signed-off-by: Guo Ren Fixes: d0d8aae64566 ("RISC-V: Set maximum number of mapped pages correctly") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7cd4993f4ff2..f9f9568d689e 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -196,7 +196,7 @@ void __init setup_bootmem(void) max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); -- cgit v1.2.3 From 4025c784c573cab7e3f84746cc82b8033923ec62 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 23 Jan 2021 16:12:44 +1000 Subject: powerpc/64s: prevent recursive replay_soft_interrupts causing superfluous interrupt When an asynchronous interrupt calls irq_exit, it checks for softirqs that may have been created, and runs them. Running softirqs enables local irqs, which can replay pending interrupts causing recursion in replay_soft_interrupts. This abridged trace shows how this can occur: ! NIP replay_soft_interrupts LR interrupt_exit_kernel_prepare Call Trace: interrupt_exit_kernel_prepare (unreliable) interrupt_return --- interrupt: ea0 at __rb_reserve_next NIP __rb_reserve_next LR __rb_reserve_next Call Trace: ring_buffer_lock_reserve trace_function function_trace_call ftrace_call __do_softirq irq_exit timer_interrupt ! replay_soft_interrupts interrupt_exit_kernel_prepare interrupt_return --- interrupt: ea0 at arch_local_irq_restore This can not be prevented easily, because softirqs must not block hard irqs, so it has to be dealt with. The recursion is bounded by design in the softirq code because softirq replay disables softirqs and loops around again to check for new softirqs created while it ran, so that's not a problem. However it does mess up interrupt replay state, causing superfluous interrupts when the second replay_soft_interrupts clears a pending interrupt, leaving it still set in the first call in the 'happened' local variable. Fix this by not caching a copy of irqs_happened across interrupt handler calls. Fixes: 3282a3da25bd ("powerpc/64: Implement soft interrupt replay in C") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210123061244.2076145-1-npiggin@gmail.com --- arch/powerpc/kernel/irq.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 6b1eca53e36c..cc7a6271b6b4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -180,13 +180,18 @@ void notrace restore_interrupts(void) void replay_soft_interrupts(void) { + struct pt_regs regs; + /* - * We use local_paca rather than get_paca() to avoid all - * the debug_smp_processor_id() business in this low level - * function + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. */ - unsigned char happened = local_paca->irq_happened; - struct pt_regs regs; ppc_save_regs(®s); regs.softe = IRQS_ENABLED; @@ -209,7 +214,7 @@ again: * This is a higher priority interrupt than the others, so * replay it first. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { local_paca->irq_happened &= ~PACA_IRQ_HMI; regs.trap = 0xe60; handle_hmi_exception(®s); @@ -217,7 +222,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_DEC) { + if (local_paca->irq_happened & PACA_IRQ_DEC) { local_paca->irq_happened &= ~PACA_IRQ_DEC; regs.trap = 0x900; timer_interrupt(®s); @@ -225,7 +230,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_EE) { + if (local_paca->irq_happened & PACA_IRQ_EE) { local_paca->irq_happened &= ~PACA_IRQ_EE; regs.trap = 0x500; do_IRQ(®s); @@ -233,7 +238,7 @@ again: hard_irq_disable(); } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) regs.trap = 0x280; @@ -245,7 +250,7 @@ again: } /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { local_paca->irq_happened &= ~PACA_IRQ_PMI; regs.trap = 0xf00; performance_monitor_exception(®s); @@ -253,8 +258,7 @@ again: hard_irq_disable(); } - happened = local_paca->irq_happened; - if (happened & ~PACA_IRQ_HARD_DIS) { + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { /* * We are responding to the next interrupt, so interrupt-off * latencies should be reset here. -- cgit v1.2.3 From 519ea6f1c82fcdc9842908155ae379de47818778 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Tue, 26 Jan 2021 13:40:56 +0000 Subject: arm64: Fix kernel address detection of __is_lm_address() Currently, the __is_lm_address() check just masks out the top 12 bits of the address, but if they are 0, it still yields a true result. This has as a side effect that virt_addr_valid() returns true even for invalid virtual addresses (e.g. 0x0). Fix the detection checking that it's actually a kernel address starting at PAGE_OFFSET. Fixes: 68dd8ef32162 ("arm64: memory: Fix virt_addr_valid() using __is_lm_address()") Cc: # 5.4.x Cc: Will Deacon Suggested-by: Catalin Marinas Reviewed-by: Catalin Marinas Acked-by: Mark Rutland Signed-off-by: Vincenzo Frascino Link: https://lore.kernel.org/r/20210126134056.45747-1-vincenzo.frascino@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/memory.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 18fce223b67b..99d7e1494aaa 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -247,9 +247,11 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address space. + * Check whether an arbitrary address is within the linear map, which + * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the + * kernel's TTBR1 address range. */ -#define __is_lm_address(addr) (((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) +#define __is_lm_address(addr) (((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) -- cgit v1.2.3 From 30596ae0547dbda469d31a2678d9072fb0a3fa27 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 25 Jan 2021 20:39:05 -0600 Subject: ARM: zImage: atags_to_fdt: Fix node names on added root nodes Commit 7536c7e03e74 ("of/fdt: Remove redundant kbasename function call") exposed a bug creating DT nodes in the ATAGS to DT fixup code. Non-existent nodes would mistaken get created with a leading '/'. The problem was fdt_path_offset() takes a full path while creating a node with fdt_add_subnode() takes just the basename. Since this we only add root child nodes, we can just skip over the '/'. Fixes: 7536c7e03e74 ("of/fdt: Remove redundant kbasename function call") Reported-by: Chris Packham Cc: Qi Zheng Cc: Russell King Signed-off-by: Rob Herring Tested-by: Chris Packham Link: https://lore.kernel.org/r/20210126023905.1631161-1-robh@kernel.org --- arch/arm/boot/compressed/atags_to_fdt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 8452753efebe..31927d2fe297 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -15,7 +15,8 @@ static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); if (offset == -FDT_ERR_NOTFOUND) - offset = fdt_add_subnode(fdt, 0, node_path); + /* Add the node to root if not found, dropping the leading '/' */ + offset = fdt_add_subnode(fdt, 0, node_path + 1); return offset; } -- cgit v1.2.3 From e82080e1f456467cc185fe65ee69fe9f9bd0b576 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 13 Jan 2021 11:56:26 -0500 Subject: s390: uv: Fix sysfs max number of VCPUs reporting The number reported by the query is N-1 and I think people reading the sysfs file would expect N instead. For users creating VMs there's no actual difference because KVM's limit is currently below the UV's limit. Signed-off-by: Janosch Frank Fixes: a0f60f8431999 ("s390/protvirt: Add sysfs firmware interface for Ultravisor information") Cc: stable@vger.kernel.org Reviewed-by: Claudio Imbrenda Acked-by: Cornelia Huck Signed-off-by: Vasily Gorbik --- arch/s390/boot/uv.c | 2 +- arch/s390/include/asm/uv.h | 4 ++-- arch/s390/kernel/uv.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index a15c033f53ca..87641dd65ccf 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -35,7 +35,7 @@ void uv_query_info(void) uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; - uv_info.max_guest_cpus = uvcb.max_guest_cpus; + uv_info.max_guest_cpu_id = uvcb.max_guest_cpu_id; } #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0325fc0469b7..7b98d4caee77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -96,7 +96,7 @@ struct uv_cb_qui { u32 max_num_sec_conf; u64 max_guest_stor_addr; u8 reserved88[158 - 136]; - u16 max_guest_cpus; + u16 max_guest_cpu_id; u8 reserveda0[200 - 160]; } __packed __aligned(8); @@ -273,7 +273,7 @@ struct uv_info { unsigned long guest_cpu_stor_len; unsigned long max_sec_stor_addr; unsigned int max_num_sec_conf; - unsigned short max_guest_cpus; + unsigned short max_guest_cpu_id; }; extern struct uv_info uv_info; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 883bfed9f5c2..b2d2ad153067 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -368,7 +368,7 @@ static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return scnprintf(page, PAGE_SIZE, "%d\n", - uv_info.max_guest_cpus); + uv_info.max_guest_cpu_id + 1); } static struct kobj_attribute uv_query_max_guest_cpus_attr = -- cgit v1.2.3