From f2c5092190f21e02d384f750bcc473554f3aa3f8 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 14 Jun 2022 20:18:14 +0200 Subject: arch/*: Disable softirq stacks on PREEMPT_RT. PREEMPT_RT preempts softirqs and the current implementation avoids do_softirq_own_stack() and only uses __do_softirq(). Disable the unused softirqs stacks on PREEMPT_RT to save some memory and ensure that do_softirq_own_stack() is not used bwcause it is not expected. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Arnd Bergmann --- arch/arm/kernel/irq.c | 3 ++- arch/parisc/kernel/irq.c | 2 ++ arch/powerpc/kernel/irq.c | 4 ++++ arch/s390/include/asm/softirq_stack.h | 3 ++- arch/sh/kernel/irq.c | 2 ++ arch/sparc/kernel/irq_64.c | 2 ++ 6 files changed, 14 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 5c6f8d11a3ce..034cb48c9eeb 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -70,6 +70,7 @@ static void __init init_irq_stacks(void) } } +#ifndef CONFIG_PREEMPT_RT static void ____do_softirq(void *arg) { __do_softirq(); @@ -80,7 +81,7 @@ void do_softirq_own_stack(void) call_with_stack(____do_softirq, NULL, __this_cpu_read(irq_stack_ptr)); } - +#endif #endif int arch_show_interrupts(struct seq_file *p, int prec) diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 0fe2d79fb123..eba193bcdab1 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -480,10 +480,12 @@ static void execute_on_irq_stack(void *func, unsigned long param1) *irq_stack_in_use = 1; } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { execute_on_irq_stack(__do_softirq, 0); } +#endif #endif /* CONFIG_IRQSTACKS */ /* ONLY called from entry.S:intr_extint() */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index dd09919c3c66..0822a274a549 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -611,6 +611,7 @@ static inline void check_stack_overflow(void) } } +#ifndef CONFIG_PREEMPT_RT static __always_inline void call_do_softirq(const void *sp) { /* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */ @@ -629,6 +630,7 @@ static __always_inline void call_do_softirq(const void *sp) "r11", "r12" ); } +#endif static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) { @@ -747,10 +749,12 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly; void *softirq_ctx[NR_CPUS] __read_mostly; void *hardirq_ctx[NR_CPUS] __read_mostly; +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { call_do_softirq(softirq_ctx[smp_processor_id()]); } +#endif irq_hw_number_t virq_to_hw(unsigned int virq) { diff --git a/arch/s390/include/asm/softirq_stack.h b/arch/s390/include/asm/softirq_stack.h index fd17f25704bd..af68d6c1d584 100644 --- a/arch/s390/include/asm/softirq_stack.h +++ b/arch/s390/include/asm/softirq_stack.h @@ -5,9 +5,10 @@ #include #include +#ifndef CONFIG_PREEMPT_RT static inline void do_softirq_own_stack(void) { call_on_stack(0, S390_lowcore.async_stack, void, __do_softirq); } - +#endif #endif /* __ASM_S390_SOFTIRQ_STACK_H */ diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index ef0f0827cf57..2d3eca8fee01 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -149,6 +149,7 @@ void irq_ctx_exit(int cpu) hardirq_ctx[cpu] = NULL; } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { struct thread_info *curctx; @@ -176,6 +177,7 @@ void do_softirq_own_stack(void) "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" ); } +#endif #else static inline void handle_one_irq(unsigned int irq) { diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index c8848bb681a1..41fa1be980a3 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -855,6 +855,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs) set_irq_regs(old_regs); } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { void *orig_sp, *sp = softirq_stack[smp_processor_id()]; @@ -869,6 +870,7 @@ void do_softirq_own_stack(void) __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) -- cgit v1.2.3 From 548927e0312194167f7ee5de47d50c2036088cce Mon Sep 17 00:00:00 2001 From: Sai Prakash Ranjan Date: Wed, 18 May 2022 22:14:10 +0530 Subject: arm64: io: Use asm-generic high level MMIO accessors Remove custom arm64 MMIO accessors read{b,w,l,q} and their relaxed versions in support to use asm-generic defined accessors. Also define one set of IO barriers (ar/bw version) used by asm-generic code to override the arm64 specific variants. Suggested-by: Arnd Bergmann Signed-off-by: Sai Prakash Ranjan Reviewed-by: Arnd Bergmann Acked-by: Catalin Marinas Signed-off-by: Arnd Bergmann --- arch/arm64/include/asm/io.h | 41 ++++++++--------------------------------- 1 file changed, 8 insertions(+), 33 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 3995652daf81..f7cd0e01bfdd 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -91,7 +91,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) } /* IO barriers */ -#define __iormb(v) \ +#define __io_ar(v) \ ({ \ unsigned long tmp; \ \ @@ -108,39 +108,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) : "memory"); \ }) -#define __io_par(v) __iormb(v) -#define __iowmb() dma_wmb() -#define __iomb() dma_mb() - -/* - * Relaxed I/O memory access primitives. These follow the Device memory - * ordering rules but do not guarantee any ordering relative to Normal memory - * accesses. - */ -#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; }) -#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; }) -#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; }) -#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; }) +#define __io_bw() dma_wmb() +#define __io_br(v) +#define __io_aw(v) -#define writeb_relaxed(v,c) ((void)__raw_writeb((v),(c))) -#define writew_relaxed(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c))) -#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c))) -#define writeq_relaxed(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c))) - -/* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. - */ -#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(__v); __v; }) -#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(__v); __v; }) -#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; }) -#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; }) - -#define writeb(v,c) ({ __iowmb(); writeb_relaxed((v),(c)); }) -#define writew(v,c) ({ __iowmb(); writew_relaxed((v),(c)); }) -#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c)); }) -#define writeq(v,c) ({ __iowmb(); writeq_relaxed((v),(c)); }) +/* arm64-specific, don't use in portable drivers */ +#define __iormb(v) __io_ar(v) +#define __iowmb() __io_bw() +#define __iomb() dma_mb() /* * I/O port access primitives. -- cgit v1.2.3 From d593d64f043add170d8ea9cf698449637917dcf9 Mon Sep 17 00:00:00 2001 From: Prasad Sodagudi Date: Wed, 18 May 2022 22:14:14 +0530 Subject: lib: Add register read/write tracing support Generic MMIO read/write i.e., __raw_{read,write}{b,l,w,q} accessors are typically used to read/write from/to memory mapped registers and can cause hangs or some undefined behaviour in following few cases, * If the access to the register space is unclocked, for example: if there is an access to multimedia(MM) block registers without MM clocks. * If the register space is protected and not set to be accessible from non-secure world, for example: only EL3 (EL: Exception level) access is allowed and any EL2/EL1 access is forbidden. * If xPU(memory/register protection units) is controlling access to certain memory/register space for specific clients. and more... Such cases usually results in instant reboot/SErrors/NOC or interconnect hangs and tracing these register accesses can be very helpful to debug such issues during initial development stages and also in later stages. So use ftrace trace events to log such MMIO register accesses which provides rich feature set such as early enablement of trace events, filtering capability, dumping ftrace logs on console and many more. Sample output: rwmmio_write: __qcom_geni_serial_console_write+0x160/0x1e0 width=32 val=0xa0d5d addr=0xfffffbfffdbff700 rwmmio_post_write: __qcom_geni_serial_console_write+0x160/0x1e0 width=32 val=0xa0d5d addr=0xfffffbfffdbff700 rwmmio_read: qcom_geni_serial_poll_bit+0x94/0x138 width=32 addr=0xfffffbfffdbff610 rwmmio_post_read: qcom_geni_serial_poll_bit+0x94/0x138 width=32 val=0x0 addr=0xfffffbfffdbff610 Co-developed-by: Sai Prakash Ranjan Signed-off-by: Prasad Sodagudi Signed-off-by: Sai Prakash Ranjan Acked-by: Steven Rostedt (Google) Signed-off-by: Arnd Bergmann --- arch/Kconfig | 3 ++ arch/arm64/Kconfig | 1 + include/trace/events/rwmmio.h | 97 +++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig | 7 ++++ lib/Makefile | 2 + lib/trace_readwrite.c | 47 +++++++++++++++++++++ 6 files changed, 157 insertions(+) create mode 100644 include/trace/events/rwmmio.h create mode 100644 lib/trace_readwrite.c (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index fcf9a41a4ef5..47899446483b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1396,6 +1396,9 @@ config ARCH_HAS_ELFCORE_COMPAT config ARCH_HAS_PARANOID_L1D_FLUSH bool +config ARCH_HAVE_TRACE_MMIO_ACCESS + bool + config DYNAMIC_SIGFRAME bool diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1652a9800ebe..fbf21e01f0b6 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -49,6 +49,7 @@ config ARM64 select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_HAVE_TRACE_MMIO_ACCESS select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION diff --git a/include/trace/events/rwmmio.h b/include/trace/events/rwmmio.h new file mode 100644 index 000000000000..de41159216c1 --- /dev/null +++ b/include/trace/events/rwmmio.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rwmmio + +#if !defined(_TRACE_RWMMIO_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RWMMIO_H + +#include + +DECLARE_EVENT_CLASS(rwmmio_rw_template, + + TP_PROTO(unsigned long caller, u64 val, u8 width, volatile void __iomem *addr), + + TP_ARGS(caller, val, width, addr), + + TP_STRUCT__entry( + __field(unsigned long, caller) + __field(unsigned long, addr) + __field(u64, val) + __field(u8, width) + ), + + TP_fast_assign( + __entry->caller = caller; + __entry->val = val; + __entry->addr = (unsigned long)addr; + __entry->width = width; + ), + + TP_printk("%pS width=%d val=%#llx addr=%#lx", + (void *)__entry->caller, __entry->width, + __entry->val, __entry->addr) +); + +DEFINE_EVENT(rwmmio_rw_template, rwmmio_write, + TP_PROTO(unsigned long caller, u64 val, u8 width, volatile void __iomem *addr), + TP_ARGS(caller, val, width, addr) +); + +DEFINE_EVENT(rwmmio_rw_template, rwmmio_post_write, + TP_PROTO(unsigned long caller, u64 val, u8 width, volatile void __iomem *addr), + TP_ARGS(caller, val, width, addr) +); + +TRACE_EVENT(rwmmio_read, + + TP_PROTO(unsigned long caller, u8 width, const volatile void __iomem *addr), + + TP_ARGS(caller, width, addr), + + TP_STRUCT__entry( + __field(unsigned long, caller) + __field(unsigned long, addr) + __field(u8, width) + ), + + TP_fast_assign( + __entry->caller = caller; + __entry->addr = (unsigned long)addr; + __entry->width = width; + ), + + TP_printk("%pS width=%d addr=%#lx", + (void *)__entry->caller, __entry->width, __entry->addr) +); + +TRACE_EVENT(rwmmio_post_read, + + TP_PROTO(unsigned long caller, u64 val, u8 width, const volatile void __iomem *addr), + + TP_ARGS(caller, val, width, addr), + + TP_STRUCT__entry( + __field(unsigned long, caller) + __field(unsigned long, addr) + __field(u64, val) + __field(u8, width) + ), + + TP_fast_assign( + __entry->caller = caller; + __entry->val = val; + __entry->addr = (unsigned long)addr; + __entry->width = width; + ), + + TP_printk("%pS width=%d val=%#llx addr=%#lx", + (void *)__entry->caller, __entry->width, + __entry->val, __entry->addr) +); + +#endif /* _TRACE_RWMMIO_H */ + +#include diff --git a/lib/Kconfig b/lib/Kconfig index 6a843639814f..80aeceee88ed 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -118,6 +118,13 @@ config INDIRECT_IOMEM_FALLBACK mmio accesses when the IO memory address is not a registered emulated region. +config TRACE_MMIO_ACCESS + bool "Register read/write tracing" + depends on TRACING && ARCH_HAVE_TRACE_MMIO_ACCESS + help + Create tracepoints for MMIO read/write operations. These trace events + can be used for logging all MMIO read/write operations. + source "lib/crypto/Kconfig" config CRC_CCITT diff --git a/lib/Makefile b/lib/Makefile index ea54294d73bf..07917a40c91f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -151,6 +151,8 @@ lib-y += logic_pio.o lib-$(CONFIG_INDIRECT_IOMEM) += logic_iomem.o +obj-$(CONFIG_TRACE_MMIO_ACCESS) += trace_readwrite.o + obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o obj-$(CONFIG_BTREE) += btree.o diff --git a/lib/trace_readwrite.c b/lib/trace_readwrite.c new file mode 100644 index 000000000000..88637038b30c --- /dev/null +++ b/lib/trace_readwrite.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Register read and write tracepoints + * + * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#ifdef CONFIG_TRACE_MMIO_ACCESS +void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr) +{ + trace_rwmmio_write(caller_addr, val, width, addr); +} +EXPORT_SYMBOL_GPL(log_write_mmio); +EXPORT_TRACEPOINT_SYMBOL_GPL(rwmmio_write); + +void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr) +{ + trace_rwmmio_post_write(caller_addr, val, width, addr); +} +EXPORT_SYMBOL_GPL(log_post_write_mmio); +EXPORT_TRACEPOINT_SYMBOL_GPL(rwmmio_post_write); + +void log_read_mmio(u8 width, const volatile void __iomem *addr, + unsigned long caller_addr) +{ + trace_rwmmio_read(caller_addr, width, addr); +} +EXPORT_SYMBOL_GPL(log_read_mmio); +EXPORT_TRACEPOINT_SYMBOL_GPL(rwmmio_read); + +void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr, + unsigned long caller_addr) +{ + trace_rwmmio_post_read(caller_addr, val, width, addr); +} +EXPORT_SYMBOL_GPL(log_post_read_mmio); +EXPORT_TRACEPOINT_SYMBOL_GPL(rwmmio_post_read); +#endif /* CONFIG_TRACE_MMIO_ACCESS */ -- cgit v1.2.3 From 451f2f1c908ba6225e2de82c53eae399f9d342c0 Mon Sep 17 00:00:00 2001 From: Sai Prakash Ranjan Date: Wed, 18 May 2022 22:14:15 +0530 Subject: KVM: arm64: Add a flag to disable MMIO trace for nVHE KVM Add a generic flag (__DISABLE_TRACE_MMIO__) to disable MMIO tracing in nVHE KVM as the tracepoint and MMIO logging symbols should not be visible at nVHE KVM as there is no way to execute them. It can also be used to disable MMIO tracing for specific drivers. Signed-off-by: Sai Prakash Ranjan Signed-off-by: Arnd Bergmann --- arch/arm64/kvm/hyp/nvhe/Makefile | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index f9fe4dc21b1f..87d22a18b7a5 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -4,7 +4,12 @@ # asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS + +# Tracepoint and MMIO logging symbols should not be visible at nVHE KVM as +# there is no way to execute them and any such MMIO access from nVHE KVM +# will explode instantly (Words of Marc Zyngier). So introduce a generic flag +# __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM. +ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__ hostprogs := gen-hyprel HOST_EXTRACFLAGS += -I$(objtree)/include -- cgit v1.2.3 From 4313a24985f00340eeb591fd66aa2b257b9e0a69 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 23 May 2022 21:59:02 +0200 Subject: arch/*/: remove CONFIG_VIRT_TO_BUS All architecture-independent users of virt_to_bus() and bus_to_virt() have been fixed to use the dma mapping interfaces or have been removed now. This means the definitions on most architectures, and the CONFIG_VIRT_TO_BUS symbol are now obsolete and can be removed. The only exceptions to this are a few network and scsi drivers for m68k Amiga and VME machines and ppc32 Macintosh. These drivers work correctly with the old interfaces and are probably not worth changing. On alpha and parisc, virt_to_bus() were still used in asm/floppy.h. alpha can use isa_virt_to_bus() like x86 does, and parisc can just open-code the virt_to_phys() here, as this is architecture specific code. I tried updating the bus-virt-phys-mapping.rst documentation, which started as an email from Linus to explain some details of the Linux-2.0 driver interfaces. The bits about virt_to_bus() were declared obsolete backin 2000, and the rest is not all that relevant any more, so in the end I just decided to remove the file completely. Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Acked-by: Michael Ellerman (powerpc) Acked-by: Helge Deller # parisc Signed-off-by: Arnd Bergmann --- Documentation/core-api/bus-virt-phys-mapping.rst | 220 --------------------- Documentation/core-api/dma-api-howto.rst | 14 -- Documentation/core-api/index.rst | 1 - .../translations/zh_CN/core-api/index.rst | 1 - arch/alpha/Kconfig | 1 - arch/alpha/include/asm/floppy.h | 2 +- arch/alpha/include/asm/io.h | 8 +- arch/ia64/Kconfig | 1 - arch/ia64/include/asm/io.h | 8 - arch/m68k/Kconfig | 1 - arch/m68k/include/asm/virtconvert.h | 4 +- arch/microblaze/Kconfig | 1 - arch/microblaze/include/asm/io.h | 2 - arch/mips/Kconfig | 1 - arch/mips/include/asm/io.h | 9 - arch/parisc/Kconfig | 1 - arch/parisc/include/asm/floppy.h | 4 +- arch/parisc/include/asm/io.h | 2 - arch/powerpc/Kconfig | 1 - arch/powerpc/include/asm/io.h | 2 - arch/riscv/include/asm/page.h | 1 - arch/x86/Kconfig | 1 - arch/x86/include/asm/io.h | 9 - arch/xtensa/Kconfig | 1 - arch/xtensa/include/asm/io.h | 3 - include/asm-generic/io.h | 14 -- mm/Kconfig | 8 - 27 files changed, 10 insertions(+), 311 deletions(-) delete mode 100644 Documentation/core-api/bus-virt-phys-mapping.rst (limited to 'arch') diff --git a/Documentation/core-api/bus-virt-phys-mapping.rst b/Documentation/core-api/bus-virt-phys-mapping.rst deleted file mode 100644 index c72b24a7d52c..000000000000 --- a/Documentation/core-api/bus-virt-phys-mapping.rst +++ /dev/null @@ -1,220 +0,0 @@ -========================================================== -How to access I/O mapped memory from within device drivers -========================================================== - -:Author: Linus - -.. warning:: - - The virt_to_bus() and bus_to_virt() functions have been - superseded by the functionality provided by the PCI DMA interface - (see Documentation/core-api/dma-api-howto.rst). They continue - to be documented below for historical purposes, but new code - must not use them. --davidm 00/12/12 - -:: - - [ This is a mail message in response to a query on IO mapping, thus the - strange format for a "document" ] - -The AHA-1542 is a bus-master device, and your patch makes the driver give the -controller the physical address of the buffers, which is correct on x86 -(because all bus master devices see the physical memory mappings directly). - -However, on many setups, there are actually **three** different ways of looking -at memory addresses, and in this case we actually want the third, the -so-called "bus address". - -Essentially, the three ways of addressing memory are (this is "real memory", -that is, normal RAM--see later about other details): - - - CPU untranslated. This is the "physical" address. Physical address - 0 is what the CPU sees when it drives zeroes on the memory bus. - - - CPU translated address. This is the "virtual" address, and is - completely internal to the CPU itself with the CPU doing the appropriate - translations into "CPU untranslated". - - - bus address. This is the address of memory as seen by OTHER devices, - not the CPU. Now, in theory there could be many different bus - addresses, with each device seeing memory in some device-specific way, but - happily most hardware designers aren't actually actively trying to make - things any more complex than necessary, so you can assume that all - external hardware sees the memory the same way. - -Now, on normal PCs the bus address is exactly the same as the physical -address, and things are very simple indeed. However, they are that simple -because the memory and the devices share the same address space, and that is -not generally necessarily true on other PCI/ISA setups. - -Now, just as an example, on the PReP (PowerPC Reference Platform), the -CPU sees a memory map something like this (this is from memory):: - - 0-2 GB "real memory" - 2 GB-3 GB "system IO" (inb/out and similar accesses on x86) - 3 GB-4 GB "IO memory" (shared memory over the IO bus) - -Now, that looks simple enough. However, when you look at the same thing from -the viewpoint of the devices, you have the reverse, and the physical memory -address 0 actually shows up as address 2 GB for any IO master. - -So when the CPU wants any bus master to write to physical memory 0, it -has to give the master address 0x80000000 as the memory address. - -So, for example, depending on how the kernel is actually mapped on the -PPC, you can end up with a setup like this:: - - physical address: 0 - virtual address: 0xC0000000 - bus address: 0x80000000 - -where all the addresses actually point to the same thing. It's just seen -through different translations.. - -Similarly, on the Alpha, the normal translation is:: - - physical address: 0 - virtual address: 0xfffffc0000000000 - bus address: 0x40000000 - -(but there are also Alphas where the physical address and the bus address -are the same). - -Anyway, the way to look up all these translations, you do:: - - #include - - phys_addr = virt_to_phys(virt_addr); - virt_addr = phys_to_virt(phys_addr); - bus_addr = virt_to_bus(virt_addr); - virt_addr = bus_to_virt(bus_addr); - -Now, when do you need these? - -You want the **virtual** address when you are actually going to access that -pointer from the kernel. So you can have something like this:: - - /* - * this is the hardware "mailbox" we use to communicate with - * the controller. The controller sees this directly. - */ - struct mailbox { - __u32 status; - __u32 bufstart; - __u32 buflen; - .. - } mbox; - - unsigned char * retbuffer; - - /* get the address from the controller */ - retbuffer = bus_to_virt(mbox.bufstart); - switch (retbuffer[0]) { - case STATUS_OK: - ... - -on the other hand, you want the bus address when you have a buffer that -you want to give to the controller:: - - /* ask the controller to read the sense status into "sense_buffer" */ - mbox.bufstart = virt_to_bus(&sense_buffer); - mbox.buflen = sizeof(sense_buffer); - mbox.status = 0; - notify_controller(&mbox); - -And you generally **never** want to use the physical address, because you can't -use that from the CPU (the CPU only uses translated virtual addresses), and -you can't use it from the bus master. - -So why do we care about the physical address at all? We do need the physical -address in some cases, it's just not very often in normal code. The physical -address is needed if you use memory mappings, for example, because the -"remap_pfn_range()" mm function wants the physical address of the memory to -be remapped as measured in units of pages, a.k.a. the pfn (the memory -management layer doesn't know about devices outside the CPU, so it -shouldn't need to know about "bus addresses" etc). - -.. note:: - - The above is only one part of the whole equation. The above - only talks about "real memory", that is, CPU memory (RAM). - -There is a completely different type of memory too, and that's the "shared -memory" on the PCI or ISA bus. That's generally not RAM (although in the case -of a video graphics card it can be normal DRAM that is just used for a frame -buffer), but can be things like a packet buffer in a network card etc. - -This memory is called "PCI memory" or "shared memory" or "IO memory" or -whatever, and there is only one way to access it: the readb/writeb and -related functions. You should never take the address of such memory, because -there is really nothing you can do with such an address: it's not -conceptually in the same memory space as "real memory" at all, so you cannot -just dereference a pointer. (Sadly, on x86 it **is** in the same memory space, -so on x86 it actually works to just deference a pointer, but it's not -portable). - -For such memory, you can do things like: - - - reading:: - - /* - * read first 32 bits from ISA memory at 0xC0000, aka - * C000:0000 in DOS terms - */ - unsigned int signature = isa_readl(0xC0000); - - - remapping and writing:: - - /* - * remap framebuffer PCI memory area at 0xFC000000, - * size 1MB, so that we can access it: We can directly - * access only the 640k-1MB area, so anything else - * has to be remapped. - */ - void __iomem *baseptr = ioremap(0xFC000000, 1024*1024); - - /* write a 'A' to the offset 10 of the area */ - writeb('A',baseptr+10); - - /* unmap when we unload the driver */ - iounmap(baseptr); - - - copying and clearing:: - - /* get the 6-byte Ethernet address at ISA address E000:0040 */ - memcpy_fromio(kernel_buffer, 0xE0040, 6); - /* write a packet to the driver */ - memcpy_toio(0xE1000, skb->data, skb->len); - /* clear the frame buffer */ - memset_io(0xA0000, 0, 0x10000); - -OK, that just about covers the basics of accessing IO portably. Questions? -Comments? You may think that all the above is overly complex, but one day you -might find yourself with a 500 MHz Alpha in front of you, and then you'll be -happy that your driver works ;) - -Note that kernel versions 2.0.x (and earlier) mistakenly called the -ioremap() function "vremap()". ioremap() is the proper name, but I -didn't think straight when I wrote it originally. People who have to -support both can do something like:: - - /* support old naming silliness */ - #if LINUX_VERSION_CODE < 0x020100 - #define ioremap vremap - #define iounmap vfree - #endif - -at the top of their source files, and then they can use the right names -even on 2.0.x systems. - -And the above sounds worse than it really is. Most real drivers really -don't do all that complex things (or rather: the complexity is not so -much in the actual IO accesses as in error handling and timeouts etc). -It's generally not hard to fix drivers, and in many cases the code -actually looks better afterwards:: - - unsigned long signature = *(unsigned int *) 0xC0000; - vs - unsigned long signature = readl(0xC0000); - -I think the second version actually is more readable, no? diff --git a/Documentation/core-api/dma-api-howto.rst b/Documentation/core-api/dma-api-howto.rst index 358d495456d1..828846804e25 100644 --- a/Documentation/core-api/dma-api-howto.rst +++ b/Documentation/core-api/dma-api-howto.rst @@ -707,20 +707,6 @@ to use the dma_sync_*() interfaces:: } } -Drivers converted fully to this interface should not use virt_to_bus() any -longer, nor should they use bus_to_virt(). Some drivers have to be changed a -little bit, because there is no longer an equivalent to bus_to_virt() in the -dynamic DMA mapping scheme - you have to always store the DMA addresses -returned by the dma_alloc_coherent(), dma_pool_alloc(), and dma_map_single() -calls (dma_map_sg() stores them in the scatterlist itself if the platform -supports dynamic DMA mapping in hardware) in your driver structures and/or -in the card registers. - -All drivers should be using these interfaces with no exceptions. It -is planned to completely remove virt_to_bus() and bus_to_virt() as -they are entirely deprecated. Some ports already do not provide these -as it is impossible to correctly support them. - Handling Errors =============== diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index dedd4d853329..726065a3095e 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -41,7 +41,6 @@ Library functionality that is used throughout the kernel. rbtree generic-radix-tree packing - bus-virt-phys-mapping this_cpu_ops timekeeping errseq diff --git a/Documentation/translations/zh_CN/core-api/index.rst b/Documentation/translations/zh_CN/core-api/index.rst index 26d9913fc8b6..c52175fc1b61 100644 --- a/Documentation/translations/zh_CN/core-api/index.rst +++ b/Documentation/translations/zh_CN/core-api/index.rst @@ -52,7 +52,6 @@ Todolist: circular-buffers generic-radix-tree packing - bus-virt-phys-mapping this_cpu_ops timekeeping errseq diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 7d0d26b5b3f5..97fce7386b00 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -17,7 +17,6 @@ config ALPHA select HAVE_PERF_EVENTS select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH - select VIRT_TO_BUS select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP select AUTO_IRQ_AFFINITY if SMP diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h index 588758685439..64b42d9591fc 100644 --- a/arch/alpha/include/asm/floppy.h +++ b/arch/alpha/include/asm/floppy.h @@ -20,7 +20,7 @@ #define fd_free_dma() free_dma(FLOPPY_DMA) #define fd_clear_dma_ff() clear_dma_ff(FLOPPY_DMA) #define fd_set_dma_mode(mode) set_dma_mode(FLOPPY_DMA,mode) -#define fd_set_dma_addr(addr) set_dma_addr(FLOPPY_DMA,virt_to_bus(addr)) +#define fd_set_dma_addr(addr) set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr)) #define fd_set_dma_count(count) set_dma_count(FLOPPY_DMA,count) #define fd_enable_irq() enable_irq(FLOPPY_IRQ) #define fd_disable_irq() disable_irq(FLOPPY_IRQ) diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h index c9cb554fbe54..d277189b2677 100644 --- a/arch/alpha/include/asm/io.h +++ b/arch/alpha/include/asm/io.h @@ -106,15 +106,15 @@ static inline void * phys_to_virt(unsigned long address) extern unsigned long __direct_map_base; extern unsigned long __direct_map_size; -static inline unsigned long __deprecated virt_to_bus(volatile void *address) +static inline unsigned long __deprecated isa_virt_to_bus(volatile void *address) { unsigned long phys = virt_to_phys(address); unsigned long bus = phys + __direct_map_base; return phys <= __direct_map_size ? bus : 0; } -#define isa_virt_to_bus virt_to_bus +#define isa_virt_to_bus isa_virt_to_bus -static inline void * __deprecated bus_to_virt(unsigned long address) +static inline void * __deprecated isa_bus_to_virt(unsigned long address) { void *virt; @@ -125,7 +125,7 @@ static inline void * __deprecated bus_to_virt(unsigned long address) virt = phys_to_virt(address); return (long)address <= 0 ? NULL : virt; } -#define isa_bus_to_virt bus_to_virt +#define isa_bus_to_virt isa_bus_to_virt /* * There are different chipsets to interface the Alpha CPUs to the world. diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index cb93769a9f2a..26ac8ea15a9e 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -39,7 +39,6 @@ config IA64 select HAVE_FUNCTION_DESCRIPTORS select HAVE_VIRT_CPU_ACCOUNTING select HUGETLB_PAGE_SIZE_VARIABLE if HUGETLB_PAGE - select VIRT_TO_BUS select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 6d93b923b379..ce66dfc0e719 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -96,14 +96,6 @@ extern u64 kern_mem_attribute (unsigned long phys_addr, unsigned long size); extern int valid_phys_addr_range (phys_addr_t addr, size_t count); /* efi.c */ extern int valid_mmap_phys_addr_range (unsigned long pfn, size_t count); -/* - * The following two macros are deprecated and scheduled for removal. - * Please use the PCI-DMA interface defined in instead. - */ -#define bus_to_virt phys_to_virt -#define virt_to_bus virt_to_phys -#define page_to_bus page_to_phys - # endif /* KERNEL */ /* diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 936cce42ae9a..b06faf6c0b27 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -30,7 +30,6 @@ config M68K select OLD_SIGACTION select OLD_SIGSUSPEND3 select UACCESS_MEMCPY if !MMU - select VIRT_TO_BUS select ZONE_DMA config CPU_BIG_ENDIAN diff --git a/arch/m68k/include/asm/virtconvert.h b/arch/m68k/include/asm/virtconvert.h index ca91b32dc6ef..0a27905b0036 100644 --- a/arch/m68k/include/asm/virtconvert.h +++ b/arch/m68k/include/asm/virtconvert.h @@ -33,9 +33,11 @@ static inline void *phys_to_virt(unsigned long address) /* * IO bus memory addresses are 1:1 with the physical address, + * deprecated globally but still used on two machines. */ +#if defined(CONFIG_AMIGA) || defined(CONFIG_VME) #define virt_to_bus virt_to_phys -#define bus_to_virt phys_to_virt +#endif #endif #endif diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 8cf429ad1c84..415182eeb082 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -38,7 +38,6 @@ config MICROBLAZE select OF_EARLY_FLATTREE select PCI_DOMAINS_GENERIC if PCI select PCI_SYSCALL if PCI - select VIRT_TO_BUS select CPU_NO_EFFICIENT_FFS select MMU_GATHER_NO_RANGE select SPARSE_IRQ diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index b6a57f8468f0..c1d78b8977a6 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -30,8 +30,6 @@ extern resource_size_t isa_mem_base; #define PCI_IOBASE ((void __iomem *)_IO_BASE) #define IO_SPACE_LIMIT (0xFFFFFFFF) -#define page_to_bus(page) (page_to_phys(page)) - extern void iounmap(volatile void __iomem *addr); extern void __iomem *ioremap(phys_addr_t address, unsigned long size); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index db09d45d59ec..ff0c76dfbbad 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -100,7 +100,6 @@ config MIPS select RTC_LIB select SYSCTL_EXCEPTION_TRACE select TRACE_IRQFLAGS_SUPPORT - select VIRT_TO_BUS select ARCH_HAS_ELFCORE_COMPAT select HAVE_ARCH_KCSAN if 64BIT diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 6f5c86d2bab4..cd9168f34fb7 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -147,15 +147,6 @@ static inline void *isa_bus_to_virt(unsigned long address) return phys_to_virt(address); } -/* - * However PCI ones are not necessarily 1:1 and therefore these interfaces - * are forbidden in portable PCI drivers. - * - * Allow them for x86 for legacy drivers, though. - */ -#define virt_to_bus virt_to_phys -#define bus_to_virt phys_to_virt - /* * Change "struct page" to physical address. */ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 5f2448dc5a2b..b0d68e9e2df0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -43,7 +43,6 @@ config PARISC select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE select HAVE_MOD_ARCH_SPECIFIC - select VIRT_TO_BUS select MODULES_USE_ELF_RELA select CLONE_BACKWARDS select TTY # Needed for pdc_cons.c diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h index 762cfe7778c0..b318a7df52f6 100644 --- a/arch/parisc/include/asm/floppy.h +++ b/arch/parisc/include/asm/floppy.h @@ -179,7 +179,7 @@ static void _fd_chose_dma_mode(char *addr, unsigned long size) { if(can_use_virtual_dma == 2) { if((unsigned int) addr >= (unsigned int) high_memory || - virt_to_bus(addr) >= 0x1000000 || + virt_to_phys(addr) >= 0x1000000 || _CROSS_64KB(addr, size, 0)) use_virtual_dma = 1; else @@ -215,7 +215,7 @@ static int hard_dma_setup(char *addr, unsigned long size, int mode, int io) doing_pdma = 0; clear_dma_ff(FLOPPY_DMA); set_dma_mode(FLOPPY_DMA,mode); - set_dma_addr(FLOPPY_DMA,virt_to_bus(addr)); + set_dma_addr(FLOPPY_DMA,virt_to_phys(addr)); set_dma_count(FLOPPY_DMA,size); enable_dma(FLOPPY_DMA); return 0; diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index 837ddddbac6a..42ffb60a6ea9 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -7,8 +7,6 @@ #define virt_to_phys(a) ((unsigned long)__pa(a)) #define phys_to_virt(a) __va(a) -#define virt_to_bus virt_to_phys -#define bus_to_virt phys_to_virt static inline unsigned long isa_bus_to_virt(unsigned long addr) { BUG(); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c2ce2e60c8f0..ae8ab95c4389 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -276,7 +276,6 @@ config PPC select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT - select VIRT_TO_BUS if !PPC64 # # Please keep this list sorted alphabetically. # diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index c5a5f7c9b231..73fcd5cdb662 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -985,8 +985,6 @@ static inline void * bus_to_virt(unsigned long address) } #define bus_to_virt bus_to_virt -#define page_to_bus(page) (page_to_phys(page) + PCI_DRAM_OFFSET) - #endif /* CONFIG_PPC32 */ /* access ports */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 1526e410e802..ac70b0fd9a9a 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -167,7 +167,6 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define page_to_virt(page) (pfn_to_virt(page_to_pfn(page))) #define page_to_phys(page) (pfn_to_phys(page_to_pfn(page))) -#define page_to_bus(page) (page_to_phys(page)) #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index be0b95e51df6..9a81b867c3bc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -278,7 +278,6 @@ config X86 select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select USER_STACKTRACE_SUPPORT - select VIRT_TO_BUS select HAVE_ARCH_KCSAN if X86_64 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 1870b99c3356..e9025640f634 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -169,15 +169,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) } #define isa_bus_to_virt phys_to_virt -/* - * However PCI ones are not necessarily 1:1 and therefore these interfaces - * are forbidden in portable PCI drivers. - * - * Allow them on x86 for legacy drivers, though. - */ -#define virt_to_bus virt_to_phys -#define bus_to_virt phys_to_virt - /* * The default ioremap() behavior is non-cached; if you need something * else, you probably want one of the following. diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 0b0f0172cced..92a24ed738a5 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -50,7 +50,6 @@ config XTENSA select MODULES_USE_ELF_RELA select PERF_USE_VMALLOC select TRACE_IRQFLAGS_SUPPORT - select VIRT_TO_BUS help Xtensa processors are 32-bit RISC machines designed by Tensilica primarily for embedded systems. These processors are both diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index 54188e69b988..a5b707e1c0f4 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -63,9 +63,6 @@ static inline void iounmap(volatile void __iomem *addr) xtensa_iounmap(addr); } -#define virt_to_bus virt_to_phys -#define bus_to_virt phys_to_virt - #endif /* CONFIG_MMU */ #include diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 9c5114335a2d..7197e0642757 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1142,20 +1142,6 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) } #endif -#ifdef CONFIG_VIRT_TO_BUS -#ifndef virt_to_bus -static inline unsigned long virt_to_bus(void *address) -{ - return (unsigned long)address; -} - -static inline void *bus_to_virt(unsigned long address) -{ - return (void *)address; -} -#endif -#endif - #ifndef memset_io #define memset_io memset_io /** diff --git a/mm/Kconfig b/mm/Kconfig index 169e64192e48..b7a44b17c79f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -639,14 +639,6 @@ config BOUNCE memory available to the CPU. Enabled by default when HIGHMEM is selected, but you may say n to override this. -config VIRT_TO_BUS - bool - help - An architecture should select this if it implements the - deprecated interface virt_to_bus(). All new architectures - should probably not select this. - - config MMU_NOTIFIER bool select SRCU -- cgit v1.2.3