From 8e30524dcc0d0ac1a18a5cee482b9d9cde3cb332 Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Mon, 1 Oct 2012 00:23:53 +0200 Subject: x86, acpi: Introduce x86 arch specific arch_reserve_mem_area() for e820 handling This is needed for ACPI table overriding via initrd. Beside reserving memblocks, X86 also requires to flag the memory area to E820_RESERVED or E820_ACPI in the e820 mappings to be able to io(re)map it later. Signed-off-by: Thomas Renninger Link: http://lkml.kernel.org/r/1349043837-22659-3-git-send-email-trenn@suse.de Cc: Len Brown Cc: Robert Moore Cc: Yinghai Lu Cc: Eric Piel Signed-off-by: H. Peter Anvin --- arch/x86/kernel/acpi/boot.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b2297e58c6ed..6b75777c0a8d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1700,3 +1700,9 @@ int __acpi_release_global_lock(unsigned int *lock) } while (unlikely (val != old)); return old & 0x1; } + +void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + e820_add_region(addr, size, E820_ACPI); + update_e820(); +} -- cgit v1.2.3 From 53aac44c904abbad9f474f652f099de13b5c3563 Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Mon, 1 Oct 2012 00:23:54 +0200 Subject: ACPI: Store valid ACPI tables passed via early initrd in reserved memblock areas A later patch will compare them with ACPI tables that get loaded at boot or runtime and if criteria match, a stored one is loaded. Signed-off-by: Thomas Renninger Link: http://lkml.kernel.org/r/1349043837-22659-4-git-send-email-trenn@suse.de Cc: Len Brown Cc: Robert Moore Cc: Yinghai Lu Cc: Eric Piel Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 2 + drivers/acpi/Kconfig | 9 ++++ drivers/acpi/osl.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/acpi.h | 8 ++++ 4 files changed, 141 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f4b9b80e1b95..764e543b2297 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -941,6 +941,8 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); + acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); + reserve_crashkernel(); vsmp_init(); diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 80998958cf45..8cf719547b51 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -261,6 +261,15 @@ config ACPI_CUSTOM_DSDT bool default ACPI_CUSTOM_DSDT_FILE != "" +config ACPI_INITRD_TABLE_OVERRIDE + bool "ACPI tables can be passed via uncompressed cpio in initrd" + default n + help + This option provides functionality to override arbitrary ACPI tables + via initrd. No functional change if no ACPI tables are passed via + initrd, therefore it's safe to say Y. + See Documentation/acpi/initrd_table_override.txt for details + config ACPI_BLACKLIST_YEAR int "Disable ACPI for systems before Jan 1st this year" if X86_32 default 0 diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 9eaf708f5885..b20b07903218 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -534,6 +534,128 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val, return AE_OK; } +#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE +#include +#include + +static u64 acpi_tables_addr; +static int all_tables_size; + +/* Copied from acpica/tbutils.c:acpi_tb_checksum() */ +u8 __init acpi_table_checksum(u8 *buffer, u32 length) +{ + u8 sum = 0; + u8 *end = buffer + length; + + while (buffer < end) + sum = (u8) (sum + *(buffer++)); + return sum; +} + +/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */ +static const char * const table_sigs[] = { + ACPI_SIG_BERT, ACPI_SIG_CPEP, ACPI_SIG_ECDT, ACPI_SIG_EINJ, + ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT, ACPI_SIG_MSCT, + ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT, ACPI_SIG_ASF, + ACPI_SIG_BOOT, ACPI_SIG_DBGP, ACPI_SIG_DMAR, ACPI_SIG_HPET, + ACPI_SIG_IBFT, ACPI_SIG_IVRS, ACPI_SIG_MCFG, ACPI_SIG_MCHI, + ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA, + ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT, + ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT, + ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL }; + +/* Non-fatal errors: Affected tables/files are ignored */ +#define INVALID_TABLE(x, path, name) \ + { pr_err("ACPI OVERRIDE: " x " [%s%s]\n", path, name); continue; } + +#define ACPI_HEADER_SIZE sizeof(struct acpi_table_header) + +/* Must not increase 10 or needs code modification below */ +#define ACPI_OVERRIDE_TABLES 10 + +void __init acpi_initrd_override(void *data, size_t size) +{ + int sig, no, table_nr = 0, total_offset = 0; + long offset = 0; + struct acpi_table_header *table; + char cpio_path[32] = "kernel/firmware/acpi/"; + struct cpio_data file; + struct cpio_data early_initrd_files[ACPI_OVERRIDE_TABLES]; + char *p; + + if (data == NULL || size == 0) + return; + + for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) { + file = find_cpio_data(cpio_path, data, size, &offset); + if (!file.data) + break; + + data += offset; + size -= offset; + + if (file.size < sizeof(struct acpi_table_header)) + INVALID_TABLE("Table smaller than ACPI header", + cpio_path, file.name); + + table = file.data; + + for (sig = 0; table_sigs[sig]; sig++) + if (!memcmp(table->signature, table_sigs[sig], 4)) + break; + + if (!table_sigs[sig]) + INVALID_TABLE("Unknown signature", + cpio_path, file.name); + if (file.size != table->length) + INVALID_TABLE("File length does not match table length", + cpio_path, file.name); + if (acpi_table_checksum(file.data, table->length)) + INVALID_TABLE("Bad table checksum", + cpio_path, file.name); + + pr_info("%4.4s ACPI table found in initrd [%s%s][0x%x]\n", + table->signature, cpio_path, file.name, table->length); + + all_tables_size += table->length; + early_initrd_files[table_nr].data = file.data; + early_initrd_files[table_nr].size = file.size; + table_nr++; + } + if (table_nr == 0) + return; + + acpi_tables_addr = + memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT, + all_tables_size, PAGE_SIZE); + if (!acpi_tables_addr) { + WARN_ON(1); + return; + } + /* + * Only calling e820_add_reserve does not work and the + * tables are invalid (memory got used) later. + * memblock_reserve works as expected and the tables won't get modified. + * But it's not enough on X86 because ioremap will + * complain later (used by acpi_os_map_memory) that the pages + * that should get mapped are not marked "reserved". + * Both memblock_reserve and e820_add_region (via arch_reserve_mem_area) + * works fine. + */ + memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size); + arch_reserve_mem_area(acpi_tables_addr, all_tables_size); + + p = early_ioremap(acpi_tables_addr, all_tables_size); + + for (no = 0; no < table_nr; no++) { + memcpy(p + total_offset, early_initrd_files[no].data, + early_initrd_files[no].size); + total_offset += early_initrd_files[no].size; + } + early_iounmap(p, all_tables_size); +} +#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */ + acpi_status acpi_os_table_override(struct acpi_table_header * existing_table, struct acpi_table_header ** new_table) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 946fd1ea79ff..d14081c10c17 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -76,6 +76,14 @@ typedef int (*acpi_table_handler) (struct acpi_table_header *table); typedef int (*acpi_table_entry_handler) (struct acpi_subtable_header *header, const unsigned long end); +#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE +void acpi_initrd_override(void *data, size_t size); +#else +static inline void acpi_initrd_override(void *data, size_t size) +{ +} +#endif + char * __acpi_map_table (unsigned long phys_addr, unsigned long size); void __acpi_unmap_table(char *map, unsigned long size); int early_acpi_boot_init(void); -- cgit v1.2.3 From 3dfd8235002727dbd759bb0f80f8ac862f392071 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 1 Oct 2012 20:38:47 -0700 Subject: ACPI: Fix build when disabled "ACPI: Store valid ACPI tables passed via early initrd in reserved memblock areas" breaks the build if either CONFIG_ACPI or CONFIG_BLK_DEV_INITRD is disabled: arch/x86/kernel/setup.c: In function 'setup_arch': arch/x86/kernel/setup.c:944: error: implicit declaration of function 'acpi_initrd_override' or arch/x86/built-in.o: In function `setup_arch': (.init.text+0x1397): undefined reference to `initrd_start' arch/x86/built-in.o: In function `setup_arch': (.init.text+0x139e): undefined reference to `initrd_end' The dummy acpi_initrd_override() function in acpi.h isn't defined without CONFIG_ACPI and initrd_{start,end} are declared but not defined without CONFIG_BLK_DEV_INITRD. [ hpa: applying this as a fix, but this really should be done cleaner ] Signed-off-by: David Rientjes Link: http://lkml.kernel.org/r/alpine.DEB.2.00.1210012032470.31644@chino.kir.corp.google.com Signed-off-by: H. Peter Anvin Cc: Thomas Renninger Cc: Len Brown --- arch/x86/kernel/setup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 764e543b2297..bf82c1e05464 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -941,7 +941,9 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); +#if defined(CONFIG_ACPI) && defined(CONFIG_BLK_DEV_INITRD) acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); +#endif reserve_crashkernel(); -- cgit v1.2.3 From 87b526d349b04c31d7b3a40b434eb3f825d22305 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 1 Oct 2012 11:40:45 -0700 Subject: seccomp: Make syscall skipping and nr changes more consistent This fixes two issues that could cause incompatibility between kernel versions: - If a tracer uses SECCOMP_RET_TRACE to select a syscall number higher than the largest known syscall, emulate the unknown vsyscall by returning -ENOSYS. (This is unlikely to make a noticeable difference on x86-64 due to the way the system call entry works.) - On x86-64 with vsyscall=emulate, skipped vsyscalls were buggy. This updates the documentation accordingly. Signed-off-by: Andy Lutomirski Acked-by: Will Drewry Signed-off-by: James Morris --- Documentation/prctl/seccomp_filter.txt | 74 ++++++++++++++++++++-- arch/x86/kernel/vsyscall_64.c | 110 ++++++++++++++++++--------------- kernel/seccomp.c | 13 +++- 3 files changed, 137 insertions(+), 60 deletions(-) (limited to 'arch/x86/kernel') diff --git a/Documentation/prctl/seccomp_filter.txt b/Documentation/prctl/seccomp_filter.txt index 597c3c581375..1e469ef75778 100644 --- a/Documentation/prctl/seccomp_filter.txt +++ b/Documentation/prctl/seccomp_filter.txt @@ -95,12 +95,15 @@ SECCOMP_RET_KILL: SECCOMP_RET_TRAP: Results in the kernel sending a SIGSYS signal to the triggering - task without executing the system call. The kernel will - rollback the register state to just before the system call - entry such that a signal handler in the task will be able to - inspect the ucontext_t->uc_mcontext registers and emulate - system call success or failure upon return from the signal - handler. + task without executing the system call. siginfo->si_call_addr + will show the address of the system call instruction, and + siginfo->si_syscall and siginfo->si_arch will indicate which + syscall was attempted. The program counter will be as though + the syscall happened (i.e. it will not point to the syscall + instruction). The return value register will contain an arch- + dependent value -- if resuming execution, set it to something + sensible. (The architecture dependency is because replacing + it with -ENOSYS could overwrite some useful information.) The SECCOMP_RET_DATA portion of the return value will be passed as si_errno. @@ -123,6 +126,18 @@ SECCOMP_RET_TRACE: the BPF program return value will be available to the tracer via PTRACE_GETEVENTMSG. + The tracer can skip the system call by changing the syscall number + to -1. Alternatively, the tracer can change the system call + requested by changing the system call to a valid syscall number. If + the tracer asks to skip the system call, then the system call will + appear to return the value that the tracer puts in the return value + register. + + The seccomp check will not be run again after the tracer is + notified. (This means that seccomp-based sandboxes MUST NOT + allow use of ptrace, even of other sandboxed processes, without + extreme care; ptracers can use this mechanism to escape.) + SECCOMP_RET_ALLOW: Results in the system call being executed. @@ -161,3 +176,50 @@ architecture supports both ptrace_event and seccomp, it will be able to support seccomp filter with minor fixup: SIGSYS support and seccomp return value checking. Then it must just add CONFIG_HAVE_ARCH_SECCOMP_FILTER to its arch-specific Kconfig. + + + +Caveats +------- + +The vDSO can cause some system calls to run entirely in userspace, +leading to surprises when you run programs on different machines that +fall back to real syscalls. To minimize these surprises on x86, make +sure you test with +/sys/devices/system/clocksource/clocksource0/current_clocksource set to +something like acpi_pm. + +On x86-64, vsyscall emulation is enabled by default. (vsyscalls are +legacy variants on vDSO calls.) Currently, emulated vsyscalls will honor seccomp, with a few oddities: + +- A return value of SECCOMP_RET_TRAP will set a si_call_addr pointing to + the vsyscall entry for the given call and not the address after the + 'syscall' instruction. Any code which wants to restart the call + should be aware that (a) a ret instruction has been emulated and (b) + trying to resume the syscall will again trigger the standard vsyscall + emulation security checks, making resuming the syscall mostly + pointless. + +- A return value of SECCOMP_RET_TRACE will signal the tracer as usual, + but the syscall may not be changed to another system call using the + orig_rax register. It may only be changed to -1 order to skip the + currently emulated call. Any other change MAY terminate the process. + The rip value seen by the tracer will be the syscall entry address; + this is different from normal behavior. The tracer MUST NOT modify + rip or rsp. (Do not rely on other changes terminating the process. + They might work. For example, on some kernels, choosing a syscall + that only exists in future kernels will be correctly emulated (by + returning -ENOSYS). + +To detect this quirky behavior, check for addr & ~0x0C00 == +0xFFFFFFFFFF600000. (For SECCOMP_RET_TRACE, use rip. For +SECCOMP_RET_TRAP, use siginfo->si_call_addr.) Do not check any other +condition: future kernels may improve vsyscall emulation and current +kernels in vsyscall=native mode will behave differently, but the +instructions at 0xF...F600{0,4,8,C}00 will not be system calls in these +cases. + +Note that modern systems are unlikely to use vsyscalls at all -- they +are a legacy feature and they are considerably slower than standard +syscalls. New code will use the vDSO, and vDSO-issued system calls +are indistinguishable from normal system calls. diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8d141b309046..b2e58a248b3b 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -136,19 +136,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) return nr; } -#ifdef CONFIG_SECCOMP -static int vsyscall_seccomp(struct task_struct *tsk, int syscall_nr) -{ - if (!seccomp_mode(&tsk->seccomp)) - return 0; - task_pt_regs(tsk)->orig_ax = syscall_nr; - task_pt_regs(tsk)->ax = syscall_nr; - return __secure_computing(syscall_nr); -} -#else -#define vsyscall_seccomp(_tsk, _nr) 0 -#endif - static bool write_ok_or_segv(unsigned long ptr, size_t size) { /* @@ -181,10 +168,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) { struct task_struct *tsk; unsigned long caller; - int vsyscall_nr; + int vsyscall_nr, syscall_nr, tmp; int prev_sig_on_uaccess_error; long ret; - int skip; /* * No point in checking CS -- the only way to get here is a user mode @@ -216,56 +202,84 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } tsk = current; - /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. - */ - prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error; - current_thread_info()->sig_on_uaccess_error = 1; /* + * Check for access_ok violations and find the syscall nr. + * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ - ret = -EFAULT; - skip = 0; switch (vsyscall_nr) { case 0: - skip = vsyscall_seccomp(tsk, __NR_gettimeofday); - if (skip) - break; - if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) || - !write_ok_or_segv(regs->si, sizeof(struct timezone))) - break; + !write_ok_or_segv(regs->si, sizeof(struct timezone))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_gettimeofday; + break; + + case 1: + if (!write_ok_or_segv(regs->di, sizeof(time_t))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_time; + break; + + case 2: + if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || + !write_ok_or_segv(regs->si, sizeof(unsigned))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_getcpu; + break; + } + + /* + * Handle seccomp. regs->ip must be the original value. + * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt. + * + * We could optimize the seccomp disabled case, but performance + * here doesn't matter. + */ + regs->orig_ax = syscall_nr; + regs->ax = -ENOSYS; + tmp = secure_computing(syscall_nr); + if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { + warn_bad_vsyscall(KERN_DEBUG, regs, + "seccomp tried to change syscall nr or ip"); + do_exit(SIGSYS); + } + if (tmp) + goto do_ret; /* skip requested */ + /* + * With a real vsyscall, page faults cause SIGSEGV. We want to + * preserve that behavior to make writing exploits harder. + */ + prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error; + current_thread_info()->sig_on_uaccess_error = 1; + + ret = -EFAULT; + switch (vsyscall_nr) { + case 0: ret = sys_gettimeofday( (struct timeval __user *)regs->di, (struct timezone __user *)regs->si); break; case 1: - skip = vsyscall_seccomp(tsk, __NR_time); - if (skip) - break; - - if (!write_ok_or_segv(regs->di, sizeof(time_t))) - break; - ret = sys_time((time_t __user *)regs->di); break; case 2: - skip = vsyscall_seccomp(tsk, __NR_getcpu); - if (skip) - break; - - if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || - !write_ok_or_segv(regs->si, sizeof(unsigned))) - break; - ret = sys_getcpu((unsigned __user *)regs->di, (unsigned __user *)regs->si, NULL); @@ -274,12 +288,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error; - if (skip) { - if ((long)regs->ax <= 0L) /* seccomp errno emulation */ - goto do_ret; - goto done; /* seccomp trace/trap */ - } - +check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, @@ -302,7 +311,6 @@ do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; -done: return true; sigsegv: diff --git a/kernel/seccomp.c b/kernel/seccomp.c index ee376beedaf9..5af44b593770 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -396,25 +396,29 @@ int __secure_computing(int this_syscall) #ifdef CONFIG_SECCOMP_FILTER case SECCOMP_MODE_FILTER: { int data; + struct pt_regs *regs = task_pt_regs(current); ret = seccomp_run_filters(this_syscall); data = ret & SECCOMP_RET_DATA; ret &= SECCOMP_RET_ACTION; switch (ret) { case SECCOMP_RET_ERRNO: /* Set the low-order 16-bits as a errno. */ - syscall_set_return_value(current, task_pt_regs(current), + syscall_set_return_value(current, regs, -data, 0); goto skip; case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ - syscall_rollback(current, task_pt_regs(current)); + syscall_rollback(current, regs); /* Let the filter pass back 16 bits of data. */ seccomp_send_sigsys(this_syscall, data); goto skip; case SECCOMP_RET_TRACE: /* Skip these calls if there is no tracer. */ - if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, regs, + -ENOSYS, 0); goto skip; + } /* Allow the BPF to provide the event message */ ptrace_event(PTRACE_EVENT_SECCOMP, data); /* @@ -425,6 +429,9 @@ int __secure_computing(int this_syscall) */ if (fatal_signal_pending(current)) break; + if (syscall_get_nr(current, regs) < 0) + goto skip; /* Explicit request to skip. */ + return 0; case SECCOMP_RET_ALLOW: return 0; -- cgit v1.2.3 From a47473939db20e3961b200eb00acf5fcf084d755 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 14:53:11 +0200 Subject: perf/x86: Make hardware event translations available in sysfs Add support to display hardware events translations available through the sysfs. Add 'events' group attribute under the sysfs x86 PMU record with attribute/file for each hardware event. This patch adds only backbone for PMUs to display config under 'events' directory. The specific PMU support itself will come in next patches, however this is how the sysfs group will look like: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend The file - hw event ID mapping is: file hw event ID --------------------------------------------------------------- cpu-cycles PERF_COUNT_HW_CPU_CYCLES instructions PERF_COUNT_HW_INSTRUCTIONS cache-references PERF_COUNT_HW_CACHE_REFERENCES cache-misses PERF_COUNT_HW_CACHE_MISSES branch-instructions PERF_COUNT_HW_BRANCH_INSTRUCTIONS branch-misses PERF_COUNT_HW_BRANCH_MISSES bus-cycles PERF_COUNT_HW_BUS_CYCLES stalled-cycles-frontend PERF_COUNT_HW_STALLED_CYCLES_FRONTEND stalled-cycles-backend PERF_COUNT_HW_STALLED_CYCLES_BACKEND ref-cycles PERF_COUNT_HW_REF_CPU_CYCLES Each file in the 'events' directory contains the term translation for the symbolic hw event for the currently running cpu model. # cat /sys/devices/cpu/events/stalled-cycles-backend event=0xb1,umask=0x01,inv,cmask=0x01 Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Stephane Eranian Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1349873598-12583-2-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 60 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/perf_event.h | 2 ++ 2 files changed, 62 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4a3374e61a93..9fa4c45ecad9 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1316,6 +1316,62 @@ static struct attribute_group x86_pmu_format_group = { .attrs = NULL, }; +struct perf_pmu_events_attr { + struct device_attribute attr; + u64 id; +}; + +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = \ + container_of(attr, struct perf_pmu_events_attr, attr); + + u64 config = x86_pmu.event_map(pmu_attr->id); + return x86_pmu.events_sysfs_show(page, config); +} + +#define EVENT_VAR(_id) event_attr_##_id +#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + +#define EVENT_ATTR(_name, _id) \ +static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = PERF_COUNT_HW_##_id, \ +}; + +EVENT_ATTR(cpu-cycles, CPU_CYCLES ); +EVENT_ATTR(instructions, INSTRUCTIONS ); +EVENT_ATTR(cache-references, CACHE_REFERENCES ); +EVENT_ATTR(cache-misses, CACHE_MISSES ); +EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); +EVENT_ATTR(branch-misses, BRANCH_MISSES ); +EVENT_ATTR(bus-cycles, BUS_CYCLES ); +EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); +EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); +EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); + +static struct attribute *empty_attrs; + +struct attribute *events_attr[] = { + EVENT_PTR(CPU_CYCLES), + EVENT_PTR(INSTRUCTIONS), + EVENT_PTR(CACHE_REFERENCES), + EVENT_PTR(CACHE_MISSES), + EVENT_PTR(BRANCH_INSTRUCTIONS), + EVENT_PTR(BRANCH_MISSES), + EVENT_PTR(BUS_CYCLES), + EVENT_PTR(STALLED_CYCLES_FRONTEND), + EVENT_PTR(STALLED_CYCLES_BACKEND), + EVENT_PTR(REF_CPU_CYCLES), + NULL, +}; + +static struct attribute_group x86_pmu_events_group = { + .name = "events", + .attrs = events_attr, +}; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1362,6 +1418,9 @@ static int __init init_hw_perf_events(void) x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (!x86_pmu.events_sysfs_show) + x86_pmu_events_group.attrs = &empty_attrs; + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -1651,6 +1710,7 @@ static struct attribute_group x86_pmu_attr_group = { static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, + &x86_pmu_events_group, NULL, }; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 271d25700297..6f75b6a7f37c 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -354,6 +354,8 @@ struct x86_pmu { int attr_rdpmc; struct attribute **format_attrs; + ssize_t (*events_sysfs_show)(char *page, u64 config); + /* * CPU Hotplug hooks */ -- cgit v1.2.3 From 8300daa26755c9a194776778bd822acf1fa2dbf6 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 14:53:12 +0200 Subject: perf/x86: Filter out undefined events from sysfs events attribute The sysfs events group attribute currently shows all hw events, including also undefined ones. This patch filters out all undefined events out of the sysfs events group attribute, so they don't even show up. Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1349873598-12583-3-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9fa4c45ecad9..39737a678a86 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1321,6 +1321,26 @@ struct perf_pmu_events_attr { u64 id; }; +/* + * Remove all undefined events (x86_pmu.event_map(id) == 0) + * out of events_attr attributes. + */ +static void __init filter_events(struct attribute **attrs) +{ + int i, j; + + for (i = 0; attrs[i]; i++) { + if (x86_pmu.event_map(i)) + continue; + + for (j = i; attrs[j]; j++) + attrs[j] = attrs[j + 1]; + + /* Check the shifted attr. */ + i--; + } +} + ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { @@ -1420,6 +1440,8 @@ static int __init init_hw_perf_events(void) if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; + else + filter_events(x86_pmu_events_group.attrs); pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); -- cgit v1.2.3 From 43c032febde48aabcf6d59f47cdcb7b5debbdc63 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 14:53:13 +0200 Subject: perf/x86: Add hardware events translations for Intel cpus Add support for Intel processors to display 'events' sysfs directory (/sys/devices/cpu/events/) with hw event translations: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Stephane Eranian Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1349873598-12583-4-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 40 ++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/perf_event.h | 2 ++ arch/x86/kernel/cpu/perf_event_intel.c | 2 ++ 3 files changed, 44 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 39737a678a86..8a1fa23452d6 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1392,6 +1392,46 @@ static struct attribute_group x86_pmu_events_group = { .attrs = events_attr, }; +ssize_t x86_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT); + u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; + u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; + bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); + bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); + bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); + bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); + ssize_t ret; + + /* + * We have whole page size to spend and just little data + * to write, so we can safely use sprintf. + */ + ret = sprintf(page, "event=0x%02llx", event); + + if (umask) + ret += sprintf(page + ret, ",umask=0x%02llx", umask); + + if (edge) + ret += sprintf(page + ret, ",edge"); + + if (pc) + ret += sprintf(page + ret, ",pc"); + + if (any) + ret += sprintf(page + ret, ",any"); + + if (inv) + ret += sprintf(page + ret, ",inv"); + + if (cmask) + ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); + + ret += sprintf(page + ret, "\n"); + + return ret; +} + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6f75b6a7f37c..f8aa2f6677f2 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -538,6 +538,8 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +ssize_t x86_event_sysfs_show(char *page, u64 config); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 324bb523d9d9..6106d3b44aa1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1628,6 +1628,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, .guest_get_msrs = core_guest_get_msrs, .format_attrs = intel_arch_formats_attr, + .events_sysfs_show = x86_event_sysfs_show, }; struct intel_shared_regs *allocate_shared_regs(int cpu) @@ -1766,6 +1767,7 @@ static __initconst const struct x86_pmu intel_pmu = { .pebs_aliases = intel_pebs_aliases_core2, .format_attrs = intel_arch3_formats_attr, + .events_sysfs_show = x86_event_sysfs_show, .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, -- cgit v1.2.3 From 0bf79d44133de42af01a70a1700b8bb4b6d3fb92 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 14:53:14 +0200 Subject: perf/x86: Add hardware events translations for AMD cpus Add support for AMD processors to display 'events' sysfs directory (/sys/devices/cpu/events/) with hw event translations: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Stephane Eranian Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1349873598-12583-5-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 +-- arch/x86/kernel/cpu/perf_event.h | 2 +- arch/x86/kernel/cpu/perf_event_amd.c | 9 +++++++++ arch/x86/kernel/cpu/perf_event_intel.c | 11 +++++++++-- 4 files changed, 20 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8a1fa23452d6..0a55ab2ff849 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1392,9 +1392,8 @@ static struct attribute_group x86_pmu_events_group = { .attrs = events_attr, }; -ssize_t x86_event_sysfs_show(char *page, u64 config) +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) { - u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT); u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index f8aa2f6677f2..21419b9178b4 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -538,7 +538,7 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } -ssize_t x86_event_sysfs_show(char *page, u64 config); +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); #ifdef CONFIG_CPU_SUP_AMD diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 4528ae7b6ec4..c93bc4e813a0 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev } } +static ssize_t amd_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | + (config & AMD64_EVENTSEL_EVENT) >> 24; + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, @@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = { .put_event_constraints = amd_put_event_constraints, .format_attrs = amd_format_attr, + .events_sysfs_show = amd_event_sysfs_show, .cpu_prepare = amd_pmu_cpu_prepare, .cpu_starting = amd_pmu_cpu_starting, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 6106d3b44aa1..93b9e1181f83 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = { NULL, }; +ssize_t intel_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT); + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -1628,7 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, .guest_get_msrs = core_guest_get_msrs, .format_attrs = intel_arch_formats_attr, - .events_sysfs_show = x86_event_sysfs_show, + .events_sysfs_show = intel_event_sysfs_show, }; struct intel_shared_regs *allocate_shared_regs(int cpu) @@ -1767,7 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = { .pebs_aliases = intel_pebs_aliases_core2, .format_attrs = intel_arch3_formats_attr, - .events_sysfs_show = x86_event_sysfs_show, + .events_sysfs_show = intel_event_sysfs_show, .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, -- cgit v1.2.3 From 20550a434583c78f8ff9a2819639e2bacbe58574 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 14:53:15 +0200 Subject: perf/x86: Add hardware events translations for Intel P6 cpus Add support for Intel P6 processors to display 'events' sysfs directory (/sys/devices/cpu/events/) with hw event translations: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Cc: Vince Weaver Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1349873598-12583-6-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.h | 1 + arch/x86/kernel/cpu/perf_event_p6.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 21419b9178b4..115c1ea97746 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -539,6 +539,7 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) } ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); +ssize_t intel_event_sysfs_show(char *page, u64 config); #ifdef CONFIG_CPU_SUP_AMD diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index e4dd0f7a0453..900b76b5d6ef 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -134,6 +134,8 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, .format_attrs = intel_p6_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, + }; __init int p6_pmu_init(void) -- cgit v1.2.3 From ce37f400336a34bb6e72c4700f9dcc2a41ff7163 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 8 Oct 2012 13:07:30 +0100 Subject: x86: Allow tracing of functions in arch/x86/kernel/rtc.c Move native_read_tsc() to tsc.c to allow profiling to be re-enabled for rtc.c. Signed-off-by: David Vrabel Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1349698050-6560-1-git-send-email-david.vrabel@citrix.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/Makefile | 1 - arch/x86/kernel/rtc.c | 6 ------ arch/x86/kernel/tsc.c | 6 ++++++ 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 91ce48f05f9f..9fd5eed3f8f5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_tsc.o = -pg -CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 4929c1be0ac0..801602b5d745 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - static struct resource rtc_resources[] = { [0] = { diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cfa5d4f7ca56..06ccb5073a3f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -77,6 +77,12 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif +unsigned long long native_read_tsc(void) +{ + return __native_read_tsc(); +} +EXPORT_SYMBOL(native_read_tsc); + int check_tsc_unstable(void) { return tsc_unstable; -- cgit v1.2.3 From 4d0e42cc66f4e7e0bf08b29da1ae6ebd60549c4e Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 25 Oct 2012 18:13:11 +0200 Subject: x86: Remove dead hlt_use_halt code The hlt_use_halt function returns always true and there is only one definition of it. The default_idle function can then get ride of the if ... statement and we can remove the else branch. Signed-off-by: Daniel Lezcano Cc: linaro-dev@lists.linaro.org Cc: patches@linaro.org Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1351181591-8710-1-git-send-email-daniel.lezcano@linaro.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/process.c | 39 ++++++++++++++------------------------- 1 file changed, 14 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b644e1c765dc..2f99e3121875 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -306,11 +306,6 @@ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); #endif -static inline int hlt_use_halt(void) -{ - return 1; -} - #ifndef CONFIG_SMP static inline void play_dead(void) { @@ -410,28 +405,22 @@ void cpu_idle(void) */ void default_idle(void) { - if (hlt_use_halt()) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle_rcuidle(1, smp_processor_id()); - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we + * test NEED_RESCHED: + */ + smp_mb(); - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - trace_power_end_rcuidle(smp_processor_id()); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); - } else { + if (!need_resched()) + safe_halt(); /* enables interrupts racelessly */ + else local_irq_enable(); - /* loop is done by the caller */ - cpu_relax(); - } + current_thread_info()->status |= TS_POLLING; + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); -- cgit v1.2.3 From d203f0b82481abc048e134ee4d0ea3efbee77bb1 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 15 Oct 2012 18:03:57 +0200 Subject: x86, MCA: Convert dont_log_ce, banks and tolerant Move those MCA configuration variables into struct mca_config and adjust the places they're used accordingly. Signed-off-by: Borislav Petkov Acked-by: Tony Luck --- arch/x86/include/asm/mce.h | 7 +++ arch/x86/kernel/cpu/mcheck/mce.c | 97 ++++++++++++++++++++++------------------ 2 files changed, 60 insertions(+), 44 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 54d73b1f00a0..e4060de88476 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -119,6 +119,13 @@ struct mce_log { #define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) #ifdef __KERNEL__ + +struct mca_config { + bool dont_log_ce; + u8 banks; + int tolerant; +}; + extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 46cbf8689692..10f4d256d9e8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -66,20 +66,10 @@ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -/* - * Tolerant levels: - * 0: always panic on uncorrected errors, log corrected errors - * 1: panic or SIGBUS on uncorrected errors, log corrected errors - * 2: SIGBUS or log uncorrected errors (if possible), log corrected errors - * 3: never panic or SIGBUS, log all errors (for testing only) - */ -static int tolerant __read_mostly = 1; -static int banks __read_mostly; static int rip_msr __read_mostly; static int mce_bootlog __read_mostly = -1; static int monarch_timeout __read_mostly = -1; static int mce_panic_timeout __read_mostly; -static int mce_dont_log_ce __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; @@ -87,6 +77,17 @@ int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; +struct mca_config mca_cfg __read_mostly = { + /* + * Tolerant levels: + * 0: always panic on uncorrected errors, log corrected errors + * 1: panic or SIGBUS on uncorrected errors, log corrected errors + * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors + * 3: never panic or SIGBUS, log all errors (for testing only) + */ + .tolerant = 1 +}; + /* User mode helper program triggered by machine check event */ static unsigned long mce_need_notify; static char mce_helper[128]; @@ -599,7 +600,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -631,7 +632,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); /* @@ -658,14 +659,14 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, { int i, ret = 0; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) + if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } return ret; @@ -700,7 +701,7 @@ static int mce_timed_out(u64 *t) goto out; if ((s64)*t < SPINUNIT) { /* CHECKME: Make panic default for 1 too? */ - if (tolerant < 1) + if (mca_cfg.tolerant < 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -750,7 +751,8 @@ static void mce_reign(void) * Grade the severity of the errors of all the CPUs. */ for_each_possible_cpu(cpu) { - int severity = mce_severity(&per_cpu(mces_seen, cpu), tolerant, + int severity = mce_severity(&per_cpu(mces_seen, cpu), + mca_cfg.tolerant, &nmsg); if (severity > global_worst) { msg = nmsg; @@ -764,7 +766,7 @@ static void mce_reign(void) * This dumps all the mces in the log buffer and stops the * other CPUs. */ - if (m && global_worst >= MCE_PANIC_SEVERITY && tolerant < 3) + if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Fatal Machine check", m, msg); /* @@ -777,7 +779,7 @@ static void mce_reign(void) * No machine check event found. Must be some external * source or one CPU is hung. Panic. */ - if (global_worst <= MCE_KEEP_SEVERITY && tolerant < 3) + if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Machine check from unknown source", NULL, NULL); /* @@ -946,7 +948,7 @@ static void mce_clear_state(unsigned long *toclear) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); } @@ -1022,7 +1024,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) int order; /* * If no_way_out gets set, there is no safe way to recover from this - * MCE. If tolerant is cranked up, we'll try anyway. + * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; /* @@ -1038,7 +1040,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) this_cpu_inc(mce_exception_count); - if (!banks) + if (!mca_cfg.banks) goto out; mce_gather_info(&m, regs); @@ -1065,7 +1067,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * because the first one to see it will clear it. */ order = mce_start(&no_way_out); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) continue; @@ -1093,7 +1095,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK); - severity = mce_severity(&m, tolerant, NULL); + severity = mce_severity(&m, mca_cfg.tolerant, NULL); /* * When machine check was for corrected handler don't touch, @@ -1117,7 +1119,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * When the ring overflows we just ignore the AO error. * RED-PEN add some logging mechanism when * usable_address or mce_add_ring fails. - * RED-PEN don't ignore overflow for tolerant == 0 + * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0 */ if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) mce_ring_add(m.addr >> PAGE_SHIFT); @@ -1149,7 +1151,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * issues we try to recover, or limit damage to the current * process. */ - if (tolerant < 3) { + if (mca_cfg.tolerant < 3) { if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { @@ -1377,11 +1379,13 @@ EXPORT_SYMBOL_GPL(mce_notify_irq); static int __cpuinit __mcheck_cpu_mce_banks_init(void) { int i; + u8 num_banks = mca_cfg.banks; - mce_banks = kzalloc(banks * sizeof(struct mce_bank), GFP_KERNEL); + mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL); if (!mce_banks) return -ENOMEM; - for (i = 0; i < banks; i++) { + + for (i = 0; i < num_banks; i++) { struct mce_bank *b = &mce_banks[i]; b->ctl = -1ULL; @@ -1401,7 +1405,7 @@ static int __cpuinit __mcheck_cpu_cap_init(void) rdmsrl(MSR_IA32_MCG_CAP, cap); b = cap & MCG_BANKCNT_MASK; - if (!banks) + if (!mca_cfg.banks) pr_info("CPU supports %d MCE banks\n", b); if (b > MAX_NR_BANKS) { @@ -1411,8 +1415,9 @@ static int __cpuinit __mcheck_cpu_cap_init(void) } /* Don't support asymmetric configurations today */ - WARN_ON(banks != 0 && b != banks); - banks = b; + WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks); + mca_cfg.banks = b; + if (!mce_banks) { int err = __mcheck_cpu_mce_banks_init(); @@ -1448,7 +1453,7 @@ static void __mcheck_cpu_init_generic(void) if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) @@ -1489,6 +1494,8 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { + struct mca_config *cfg = &mca_cfg; + if (c->x86_vendor == X86_VENDOR_UNKNOWN) { pr_info("unknown CPU type - not enabling MCE support\n"); return -EOPNOTSUPP; @@ -1496,7 +1503,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { - if (c->x86 == 15 && banks > 4) { + if (c->x86 == 15 && cfg->banks > 4) { /* * disable GART TBL walk error reporting, which * trips off incorrectly with the IOMMU & 3ware @@ -1515,7 +1522,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * Various K7s with broken bank 0 around. Always disable * by default. */ - if (c->x86 == 6 && banks > 0) + if (c->x86 == 6 && cfg->banks > 0) mce_banks[0].ctl = 0; /* @@ -1566,7 +1573,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * valid event later, merely don't write CTL0. */ - if (c->x86 == 6 && c->x86_model < 0x1A && banks > 0) + if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0) mce_banks[0].init = 0; /* @@ -1951,6 +1958,8 @@ static struct miscdevice mce_chrdev_device = { */ static int __init mcheck_enable(char *str) { + struct mca_config *cfg = &mca_cfg; + if (*str == 0) { enable_p5_mce(); return 1; @@ -1962,7 +1971,7 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "no_cmci")) mce_cmci_disabled = 1; else if (!strcmp(str, "dont_log_ce")) - mce_dont_log_ce = 1; + cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) @@ -1970,7 +1979,7 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bios_cmci_threshold")) mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { - get_option(&str, &tolerant); + get_option(&str, &(cfg->tolerant)); if (*str == ',') { ++str; get_option(&str, &monarch_timeout); @@ -2002,7 +2011,7 @@ static int mce_disable_error_reporting(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2190,9 +2199,9 @@ static ssize_t store_int_with_restart(struct device *s, } static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); -static DEVICE_INT_ATTR(tolerant, 0644, tolerant); +static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout); -static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce); +static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static struct dev_ext_attribute dev_attr_check_interval = { __ATTR(check_interval, 0644, device_show_int, store_int_with_restart), @@ -2253,7 +2262,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) if (err) goto error; } - for (j = 0; j < banks; j++) { + for (j = 0; j < mca_cfg.banks; j++) { err = device_create_file(dev, &mce_banks[j].attr); if (err) goto error2; @@ -2285,7 +2294,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) for (i = 0; mce_device_attrs[i]; i++) device_remove_file(dev, mce_device_attrs[i]); - for (i = 0; i < banks; i++) + for (i = 0; i < mca_cfg.banks; i++) device_remove_file(dev, &mce_banks[i].attr); device_unregister(dev); @@ -2304,7 +2313,7 @@ static void __cpuinit mce_disable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2322,7 +2331,7 @@ static void __cpuinit mce_reenable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_reenable(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2375,7 +2384,7 @@ static __init void mce_init_banks(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; struct device_attribute *a = &b->attr; -- cgit v1.2.3 From 84c2559dee2d69606f1fd4ce6563e79e7611a7b7 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 15 Oct 2012 19:59:18 +0200 Subject: x86, MCA: Convert rip_msr, mce_bootlog, monarch_timeout Move above configuration variables into struct mca_config and adjust usage places accordingly. Signed-off-by: Borislav Petkov Acked-by: Tony Luck --- arch/x86/include/asm/mce.h | 3 +++ arch/x86/kernel/cpu/mcheck/mce.c | 51 +++++++++++++++++++++------------------- 2 files changed, 30 insertions(+), 24 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index e4060de88476..73ba1853951a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -123,7 +123,10 @@ struct mce_log { struct mca_config { bool dont_log_ce; u8 banks; + s8 bootlog; int tolerant; + int monarch_timeout; + u32 rip_msr; }; extern void mce_register_decode_chain(struct notifier_block *nb); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 10f4d256d9e8..aa11019eeb0e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -66,9 +66,6 @@ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -static int rip_msr __read_mostly; -static int mce_bootlog __read_mostly = -1; -static int monarch_timeout __read_mostly = -1; static int mce_panic_timeout __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; @@ -78,6 +75,7 @@ int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; struct mca_config mca_cfg __read_mostly = { + .bootlog = -1, /* * Tolerant levels: * 0: always panic on uncorrected errors, log corrected errors @@ -85,7 +83,8 @@ struct mca_config mca_cfg __read_mostly = { * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors * 3: never panic or SIGBUS, log all errors (for testing only) */ - .tolerant = 1 + .tolerant = 1, + .monarch_timeout = -1 }; /* User mode helper program triggered by machine check event */ @@ -373,7 +372,7 @@ static int msr_to_offset(u32 msr) { unsigned bank = __this_cpu_read(injectm.bank); - if (msr == rip_msr) + if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) return offsetof(struct mce, status); @@ -452,8 +451,8 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) m->cs |= 3; } /* Use accurate RIP reporting if available. */ - if (rip_msr) - m->ip = mce_rdmsrl(rip_msr); + if (mca_cfg.rip_msr) + m->ip = mce_rdmsrl(mca_cfg.rip_msr); } } @@ -697,7 +696,7 @@ static int mce_timed_out(u64 *t) rmb(); if (atomic_read(&mce_paniced)) wait_for_panic(); - if (!monarch_timeout) + if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { /* CHECKME: Make panic default for 1 too? */ @@ -803,7 +802,7 @@ static int mce_start(int *no_way_out) { int order; int cpus = num_online_cpus(); - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) return -1; @@ -867,7 +866,7 @@ static int mce_start(int *no_way_out) static int mce_end(int order) { int ret = -1; - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) goto reset; @@ -1427,7 +1426,7 @@ static int __cpuinit __mcheck_cpu_cap_init(void) /* Use accurate RIP reporting if available. */ if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9) - rip_msr = MSR_IA32_MCG_EIP; + mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) mce_ser = 1; @@ -1437,15 +1436,19 @@ static int __cpuinit __mcheck_cpu_cap_init(void) static void __mcheck_cpu_init_generic(void) { + enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; int i; + if (!mca_cfg.bootlog) + m_fl = MCP_DONTLOG; + /* * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); + machine_check_poll(MCP_UC | m_fl, &all_banks); set_in_cr4(X86_CR4_MCE); @@ -1511,12 +1514,12 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && mce_bootlog < 0) { + if (c->x86 <= 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: */ - mce_bootlog = 0; + cfg->bootlog = 0; } /* * Various K7s with broken bank 0 around. Always disable @@ -1581,22 +1584,22 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * synchronization with a one second timeout. */ if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && - monarch_timeout < 0) - monarch_timeout = USEC_PER_SEC; + cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; /* * There are also broken BIOSes on some Pentium M and * earlier systems: */ - if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) - mce_bootlog = 0; + if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) + cfg->bootlog = 0; if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } - if (monarch_timeout < 0) - monarch_timeout = 0; - if (mce_bootlog != 0) + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = 0; + if (cfg->bootlog != 0) mce_panic_timeout = 30; return 0; @@ -1975,14 +1978,14 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "ignore_ce")) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) - mce_bootlog = (str[0] == 'b'); + cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &(cfg->tolerant)); if (*str == ',') { ++str; - get_option(&str, &monarch_timeout); + get_option(&str, &(cfg->monarch_timeout)); } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); @@ -2200,7 +2203,7 @@ static ssize_t store_int_with_restart(struct device *s, static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); -static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout); +static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static struct dev_ext_attribute dev_attr_check_interval = { -- cgit v1.2.3 From 7af19e4afdafa4adb5fffc569d5bb1c5e568ba98 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 15 Oct 2012 20:25:17 +0200 Subject: x86, MCA: Convert the next three variables batch Move them into the mca_config struct and adjust code touching them accordingly. Signed-off-by: Borislav Petkov Acked-by: Tony Luck --- arch/x86/include/asm/mce.h | 6 ++++-- arch/x86/kernel/cpu/mcheck/mce.c | 35 ++++++++++++++++------------------ arch/x86/kernel/cpu/mcheck/mce_intel.c | 2 +- 3 files changed, 21 insertions(+), 22 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 73ba1853951a..a711e3f4fbc7 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -122,13 +122,17 @@ struct mce_log { struct mca_config { bool dont_log_ce; + bool cmci_disabled; + bool ignore_ce; u8 banks; s8 bootlog; int tolerant; int monarch_timeout; + int panic_timeout; u32 rip_msr; }; +extern struct mca_config mca_cfg; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -169,8 +173,6 @@ DECLARE_PER_CPU(struct device *, mce_device); #define MAX_NR_BANKS 32 #ifdef CONFIG_X86_MCE_INTEL -extern int mce_cmci_disabled; -extern int mce_ignore_ce; extern int mce_bios_cmci_threshold; void mce_intel_feature_init(struct cpuinfo_x86 *c); void cmci_clear(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index aa11019eeb0e..8c7a90d89852 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -66,9 +66,6 @@ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -static int mce_panic_timeout __read_mostly; -int mce_cmci_disabled __read_mostly; -int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; int mce_bios_cmci_threshold __read_mostly; @@ -302,7 +299,7 @@ static void wait_for_panic(void) while (timeout-- > 0) udelay(1); if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic("Panicing machine check CPU died"); } @@ -360,7 +357,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); if (!fake_panic) { if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -1600,7 +1597,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; if (cfg->bootlog != 0) - mce_panic_timeout = 30; + cfg->panic_timeout = 30; return 0; } @@ -1645,7 +1642,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) __this_cpu_write(mce_next_interval, iv); - if (mce_ignore_ce || !iv) + if (mca_cfg.ignore_ce || !iv) return; t->expires = round_jiffies(jiffies + iv); @@ -1972,11 +1969,11 @@ static int __init mcheck_enable(char *str) if (!strcmp(str, "off")) mce_disabled = 1; else if (!strcmp(str, "no_cmci")) - mce_cmci_disabled = 1; + cfg->cmci_disabled = true; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) - mce_ignore_ce = 1; + cfg->ignore_ce = true; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) @@ -2154,15 +2151,15 @@ static ssize_t set_ignore_ce(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_ignore_ce ^ !!new) { + if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ mce_timer_delete_all(); on_each_cpu(mce_disable_cmci, NULL, 1); - mce_ignore_ce = 1; + mca_cfg.ignore_ce = true; } else { /* enable ce features */ - mce_ignore_ce = 0; + mca_cfg.ignore_ce = false; on_each_cpu(mce_enable_ce, (void *)1, 1); } } @@ -2178,14 +2175,14 @@ static ssize_t set_cmci_disabled(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_cmci_disabled ^ !!new) { + if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ on_each_cpu(mce_disable_cmci, NULL, 1); - mce_cmci_disabled = 1; + mca_cfg.cmci_disabled = true; } else { /* enable cmci */ - mce_cmci_disabled = 0; + mca_cfg.cmci_disabled = false; on_each_cpu(mce_enable_ce, NULL, 1); } } @@ -2212,13 +2209,13 @@ static struct dev_ext_attribute dev_attr_check_interval = { }; static struct dev_ext_attribute dev_attr_ignore_ce = { - __ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce), - &mce_ignore_ce + __ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce), + &mca_cfg.ignore_ce }; static struct dev_ext_attribute dev_attr_cmci_disabled = { - __ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled), - &mce_cmci_disabled + __ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled), + &mca_cfg.cmci_disabled }; static struct device_attribute *mce_device_attrs[] = { diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 5f88abf07e9c..1acd8ecba1c3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -53,7 +53,7 @@ static int cmci_supported(int *banks) { u64 cap; - if (mce_cmci_disabled || mce_ignore_ce) + if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) return 0; /* -- cgit v1.2.3 From 1462594bf2866c1dc80066ed6f49f4331c551901 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 17 Oct 2012 12:05:33 +0200 Subject: x86, MCA: Finish mca_config conversion mce_ser, mce_bios_cmci_threshold and mce_disabled are the last three bools which need conversion. Move them to the mca_config struct and adjust usage sites accordingly. Signed-off-by: Borislav Petkov Acked-by: Tony Luck --- arch/x86/include/asm/mce.h | 5 +++-- arch/x86/kernel/cpu/mcheck/mce-internal.h | 2 -- arch/x86/kernel/cpu/mcheck/mce-severity.c | 4 ++-- arch/x86/kernel/cpu/mcheck/mce.c | 36 ++++++++++++++----------------- arch/x86/kernel/cpu/mcheck/mce_intel.c | 6 +++--- arch/x86/lguest/boot.c | 2 +- 6 files changed, 25 insertions(+), 30 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index a711e3f4fbc7..d90c2fccc30c 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -124,6 +124,9 @@ struct mca_config { bool dont_log_ce; bool cmci_disabled; bool ignore_ce; + bool disabled; + bool ser; + bool bios_cmci_threshold; u8 banks; s8 bootlog; int tolerant; @@ -140,7 +143,6 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb); #include #include -extern int mce_disabled; extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE @@ -173,7 +175,6 @@ DECLARE_PER_CPU(struct device *, mce_device); #define MAX_NR_BANKS 32 #ifdef CONFIG_X86_MCE_INTEL -extern int mce_bios_cmci_threshold; void mce_intel_feature_init(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 6a05c1d327a9..5b7d4fa5d3b7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -24,8 +24,6 @@ struct mce_bank { int mce_severity(struct mce *a, int tolerant, char **msg); struct dentry *mce_get_debugfs_dir(void); -extern int mce_ser; - extern struct mce_bank *mce_banks; #ifdef CONFIG_X86_MCE_INTEL diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 13017626f9a8..beb1f1689e52 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -193,9 +193,9 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if ((m->mcgstatus & s->mcgmask) != s->mcgres) continue; - if (s->ser == SER_REQUIRED && !mce_ser) + if (s->ser == SER_REQUIRED && !mca_cfg.ser) continue; - if (s->ser == NO_SER && mce_ser) + if (s->ser == NO_SER && mca_cfg.ser) continue; if (s->context && ctx != s->context) continue; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c7a90d89852..80dbda84f1c3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -58,18 +58,13 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define CREATE_TRACE_POINTS #include -int mce_disabled __read_mostly; - #define SPINUNIT 100 /* 100ns */ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -int mce_ser __read_mostly; -int mce_bios_cmci_threshold __read_mostly; - -struct mce_bank *mce_banks __read_mostly; +struct mce_bank *mce_banks __read_mostly; struct mca_config mca_cfg __read_mostly = { .bootlog = -1, @@ -510,7 +505,7 @@ static int mce_ring_add(unsigned long pfn) int mce_available(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return 0; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -562,7 +557,7 @@ static void mce_read_aux(struct mce *m, int i) /* * Mask the reported address by the reported granularity. */ - if (mce_ser && (m->status & MCI_STATUS_MISCV)) { + if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) { u8 shift = MCI_MISC_ADDR_LSB(m->misc); m->addr >>= shift; m->addr <<= shift; @@ -617,7 +612,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * TBD do the same check for MCI_STATUS_EN here? */ if (!(flags & MCP_UC) && - (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC))) + (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; mce_read_aux(&m, i); @@ -1009,6 +1004,7 @@ static void mce_clear_info(struct mce_info *mi) */ void do_machine_check(struct pt_regs *regs, long error_code) { + struct mca_config *cfg = &mca_cfg; struct mce m, *final; int i; int worst = 0; @@ -1036,7 +1032,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) this_cpu_inc(mce_exception_count); - if (!mca_cfg.banks) + if (!cfg->banks) goto out; mce_gather_info(&m, regs); @@ -1063,7 +1059,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * because the first one to see it will clear it. */ order = mce_start(&no_way_out); - for (i = 0; i < mca_cfg.banks; i++) { + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) continue; @@ -1082,7 +1078,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Non uncorrected or non signaled errors are handled by * machine_check_poll. Leave them alone, unless this panics. */ - if (!(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && !no_way_out) continue; @@ -1091,7 +1087,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK); - severity = mce_severity(&m, mca_cfg.tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL); /* * When machine check was for corrected handler don't touch, @@ -1147,7 +1143,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * issues we try to recover, or limit damage to the current * process. */ - if (mca_cfg.tolerant < 3) { + if (cfg->tolerant < 3) { if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { @@ -1426,7 +1422,7 @@ static int __cpuinit __mcheck_cpu_cap_init(void) mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) - mce_ser = 1; + mca_cfg.ser = true; return 0; } @@ -1675,7 +1671,7 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = */ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return; if (__mcheck_cpu_ancient_init(c)) @@ -1685,7 +1681,7 @@ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) return; if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { - mce_disabled = 1; + mca_cfg.disabled = true; return; } @@ -1967,7 +1963,7 @@ static int __init mcheck_enable(char *str) if (*str == '=') str++; if (!strcmp(str, "off")) - mce_disabled = 1; + cfg->disabled = true; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; else if (!strcmp(str, "dont_log_ce")) @@ -1977,7 +1973,7 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) - mce_bios_cmci_threshold = 1; + cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { get_option(&str, &(cfg->tolerant)); if (*str == ',') { @@ -2435,7 +2431,7 @@ device_initcall_sync(mcheck_init_device); */ static int __init mcheck_disable(char *str) { - mce_disabled = 1; + mca_cfg.disabled = true; return 1; } __setup("nomce", mcheck_disable); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 1acd8ecba1c3..79b2b6b6e613 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -200,7 +200,7 @@ static void cmci_discover(int banks) continue; } - if (!mce_bios_cmci_threshold) { + if (!mca_cfg.bios_cmci_threshold) { val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; val |= CMCI_THRESHOLD; } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { @@ -227,7 +227,7 @@ static void cmci_discover(int banks) * set the thresholds properly or does not work with * this boot option. Note down now and report later. */ - if (mce_bios_cmci_threshold && bios_zero_thresh && + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) bios_wrong_thresh = 1; } else { @@ -235,7 +235,7 @@ static void cmci_discover(int banks) } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (mce_bios_cmci_threshold && bios_wrong_thresh) { + if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { pr_info_once( "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); pr_info_once( diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 642d8805bc1b..df4176cdbb32 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1412,7 +1412,7 @@ __init void lguest_init(void) /* We don't have features. We have puppies! Puppies! */ #ifdef CONFIG_X86_MCE - mce_disabled = 1; + mca_cfg.disabled = true; #endif #ifdef CONFIG_ACPI acpi_disabled = 1; -- cgit v1.2.3 From 2c5594df344cd1ff0cc9bf007dea3235582b3acf Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 26 Oct 2012 11:40:28 +0200 Subject: rcu: Fix unrecovered RCU user mode in syscall_trace_leave() On x86-64 syscall exit, 3 non exclusive events may happen looping in the following order: 1) Check if we need resched for user preemption, if so call schedule_user() 2) Check if we have pending signals, if so call do_notify_resume() 3) Check if we do syscall tracing, if so call syscall_trace_leave() However syscall_trace_leave() has been written assuming it directly follows the syscall and forget about the above possible 1st and 2nd steps. Now schedule_user() and do_notify_resume() exit in RCU user mode because they have most chances to resume userspace immediately and this avoids an rcu_user_enter() call in the syscall fast path. So by the time we call syscall_trace_leave(), we may well be in RCU user mode. To fix this up, simply call rcu_user_exit() in the beginning of this function. This fixes some reported RCU uses in extended quiescent state. Reported-by: Dave Jones Reported-by: Sergey Senozhatsky Signed-off-by: Frederic Weisbecker Tested-by: Sergey Senozhatsky Signed-off-by: Paul E. McKenney --- arch/x86/kernel/ptrace.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b00b33a18390..eff5b8c68652 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1511,6 +1511,13 @@ void syscall_trace_leave(struct pt_regs *regs) { bool step; + /* + * We may come here right after calling schedule_user() + * or do_notify_resume(), in which case we can be in RCU + * user mode. + */ + rcu_user_exit(); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) -- cgit v1.2.3 From e6d41e8c697e07832efa4a85bf23438bc4c4e1b2 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 29 Oct 2012 18:40:08 +0100 Subject: x86, AMD: Change Boris' email address Move to private email and put in maintained status. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1351532410-4887-1-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 698b6ec12e0f..1ac581f38dfa 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -6,7 +6,7 @@ * * Written by Jacob Shin - AMD, Inc. * - * Support: borislav.petkov@amd.com + * Maintained by: Borislav Petkov * * April 2006 * - added support for AMD Family 0x10 processors -- cgit v1.2.3 From 943482d07e926128eed0482b879736f912c429e4 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Mon, 29 Oct 2012 18:51:38 +0100 Subject: x86, microcode_amd: Change email addresses, MAINTAINERS entry Signed-off-by: Andreas Herrmann Cc: lm-sensors@lm-sensors.org Cc: oprofile-list@lists.sf.net Cc: Stephane Eranian Cc: Robert Richter Cc: Borislav Petkov Cc: Jorg Roedel Cc: Rafael J. Wysocki Cc: Jean Delvare Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20121029175138.GC5024@tweety Signed-off-by: Ingo Molnar --- MAINTAINERS | 4 ++-- arch/x86/kernel/microcode_amd.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/MAINTAINERS b/MAINTAINERS index e775b8749205..17403702f56a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -534,9 +534,9 @@ F: drivers/iommu/amd_iommu*.[ch] F: include/linux/amd-iommu.h AMD MICROCODE UPDATE SUPPORT -M: Andreas Herrmann +M: Andreas Herrmann L: amd64-microcode@amd64.org -S: Supported +S: Maintained F: arch/x86/kernel/microcode_amd.c AMS (Apple Motion Sensor) DRIVER diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7720ff5a9ee2..b3e67ba55b77 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -8,8 +8,8 @@ * Tigran Aivazian * * Maintainers: - * Andreas Herrmann - * Borislav Petkov + * Andreas Herrmann + * Borislav Petkov * * This driver allows to upgrade microcode on F10h AMD * CPUs and later. -- cgit v1.2.3 From 95d18aa2b6c05351181934b3bc34ce038cc7b637 Mon Sep 17 00:00:00 2001 From: Peter Huewe Date: Mon, 29 Oct 2012 21:48:17 +0100 Subject: perf/x86: Fix sparse warnings FYI, there are new sparse warnings: arch/x86/kernel/cpu/perf_event.c:1356:18: sparse: symbol 'events_attr' was not declared. Should it be static? This patch makes it static and also adds the static keyword to fix arch/x86/kernel/cpu/perf_event.c:1344:9: warning: symbol 'events_sysfs_show' was not declared. Signed-off-by: Peter Huewe Cc: Peter Zijlstra Cc: Yuanhan Liu Cc: fengguang.wu@intel.com Cc: Jiri Olsa Link: http://lkml.kernel.org/n/tip-lerdpXlnruh0yvWs2owwuizl@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 0a55ab2ff849..4428fd178bce 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1341,7 +1341,7 @@ static void __init filter_events(struct attribute **attrs) } } -ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, +static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = \ @@ -1373,7 +1373,7 @@ EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); static struct attribute *empty_attrs; -struct attribute *events_attr[] = { +static struct attribute *events_attr[] = { EVENT_PTR(CPU_CYCLES), EVENT_PTR(INSTRUCTIONS), EVENT_PTR(CACHE_REFERENCES), -- cgit v1.2.3 From da5a108d05b4f350be33e62d2db125673823e7ff Mon Sep 17 00:00:00 2001 From: Xiaoyan Zhang Date: Fri, 7 Sep 2012 19:29:04 +0100 Subject: x86/kernel: remove tboot 1:1 page table creation code For TXT boot, while Linux kernel trys to shutdown/S3/S4/reboot, it need to jump back to tboot code and do TXT teardown work. Previously kernel zapped all mem page identity mapping (va=pa) after booting, so tboot code mem address was mapped again with identity mapping. Now kernel didn't zap the identity mapping page table, so tboot related code can remove the remapping code before trapping back now. Signed-off-by: Xiaoyan Zhang Acked-by: Gang Wei Signed-off-by: Matt Fleming --- arch/x86/kernel/tboot.c | 78 ++++--------------------------------------------- 1 file changed, 5 insertions(+), 73 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index f84fe00fad48..d4f460f962ee 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -103,71 +103,13 @@ void __init tboot_probe(void) pr_debug("tboot_size: 0x%x\n", tboot->tboot_size); } -static pgd_t *tboot_pg_dir; -static struct mm_struct tboot_mm = { - .mm_rb = RB_ROOT, - .pgd = swapper_pg_dir, - .mm_users = ATOMIC_INIT(2), - .mm_count = ATOMIC_INIT(1), - .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), - .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), - .mmlist = LIST_HEAD_INIT(init_mm.mmlist), -}; - static inline void switch_to_tboot_pt(void) { - write_cr3(virt_to_phys(tboot_pg_dir)); -} - -static int map_tboot_page(unsigned long vaddr, unsigned long pfn, - pgprot_t prot) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = pgd_offset(&tboot_mm, vaddr); - pud = pud_alloc(&tboot_mm, pgd, vaddr); - if (!pud) - return -1; - pmd = pmd_alloc(&tboot_mm, pud, vaddr); - if (!pmd) - return -1; - pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr); - if (!pte) - return -1; - set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); - pte_unmap(pte); - return 0; -} - -static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn, - unsigned long nr) -{ - /* Reuse the original kernel mapping */ - tboot_pg_dir = pgd_alloc(&tboot_mm); - if (!tboot_pg_dir) - return -1; - - for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) { - if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC)) - return -1; - } - - return 0; -} - -static void tboot_create_trampoline(void) -{ - u32 map_base, map_size; - - /* Create identity map for tboot shutdown code. */ - map_base = PFN_DOWN(tboot->tboot_base); - map_size = PFN_UP(tboot->tboot_size); - if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size)) - panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n", - map_base, map_size); +#ifdef CONFIG_X86_32 + load_cr3(initial_page_table); +#else + write_cr3(real_mode_header->trampoline_pgd); +#endif } #ifdef CONFIG_ACPI_SLEEP @@ -225,14 +167,6 @@ void tboot_shutdown(u32 shutdown_type) if (!tboot_enabled()) return; - /* - * if we're being called before the 1:1 mapping is set up then just - * return and let the normal shutdown happen; this should only be - * due to very early panic() - */ - if (!tboot_pg_dir) - return; - /* if this is S3 then set regions to MAC */ if (shutdown_type == TB_SHUTDOWN_S3) if (tboot_setup_sleep()) @@ -343,8 +277,6 @@ static __init int tboot_late_init(void) if (!tboot_enabled()) return 0; - tboot_create_trampoline(); - atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); -- cgit v1.2.3 From 85b97637bb40a9f486459dd254598759af9c3d50 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Mon, 29 Oct 2012 11:01:50 +0800 Subject: x86/mce: Do not change worker's running cpu in cmci_rediscover(). cmci_rediscover() used set_cpus_allowed_ptr() to change the current process's running cpu, and migrate itself to the dest cpu. But worker processes are not allowed to be migrated. If current is a worker, the worker will be migrated to another cpu, but the corresponding worker_pool is still on the original cpu. In this case, the following BUG_ON in try_to_wake_up_local() will be triggered: BUG_ON(rq != this_rq()); This will cause the kernel panic. The call trace is like the following: [ 6155.451107] ------------[ cut here ]------------ [ 6155.452019] kernel BUG at kernel/sched/core.c:1654! ...... [ 6155.452019] RIP: 0010:[] [] try_to_wake_up_local+0x115/0x130 ...... [ 6155.452019] Call Trace: [ 6155.452019] [] __schedule+0x764/0x880 [ 6155.452019] [] schedule+0x29/0x70 [ 6155.452019] [] schedule_timeout+0x235/0x2d0 [ 6155.452019] [] ? mark_held_locks+0x8d/0x140 [ 6155.452019] [] ? __lock_release+0x133/0x1a0 [ 6155.452019] [] ? _raw_spin_unlock_irq+0x30/0x50 [ 6155.452019] [] ? trace_hardirqs_on_caller+0x105/0x190 [ 6155.452019] [] wait_for_common+0x12b/0x180 [ 6155.452019] [] ? try_to_wake_up+0x2f0/0x2f0 [ 6155.452019] [] wait_for_completion+0x1d/0x20 [ 6155.452019] [] stop_one_cpu+0x8a/0xc0 [ 6155.452019] [] ? __migrate_task+0x1a0/0x1a0 [ 6155.452019] [] ? complete+0x28/0x60 [ 6155.452019] [] set_cpus_allowed_ptr+0x128/0x130 [ 6155.452019] [] cmci_rediscover+0xf5/0x140 [ 6155.452019] [] mce_cpu_callback+0x18d/0x19d [ 6155.452019] [] notifier_call_chain+0x67/0x150 [ 6155.452019] [] __raw_notifier_call_chain+0xe/0x10 [ 6155.452019] [] __cpu_notify+0x20/0x40 [ 6155.452019] [] cpu_notify_nofail+0x15/0x30 [ 6155.452019] [] _cpu_down+0x262/0x2e0 [ 6155.452019] [] cpu_down+0x36/0x50 [ 6155.452019] [] acpi_processor_remove+0x50/0x11e [ 6155.452019] [] acpi_device_remove+0x90/0xb2 [ 6155.452019] [] __device_release_driver+0x7c/0xf0 [ 6155.452019] [] device_release_driver+0x2f/0x50 [ 6155.452019] [] acpi_bus_remove+0x32/0x6d [ 6155.452019] [] acpi_bus_trim+0x87/0xee [ 6155.452019] [] acpi_bus_hot_remove_device+0x88/0x16b [ 6155.452019] [] acpi_os_execute_deferred+0x27/0x34 [ 6155.452019] [] process_one_work+0x219/0x680 [ 6155.452019] [] ? process_one_work+0x1b8/0x680 [ 6155.452019] [] ? acpi_os_wait_events_complete+0x23/0x23 [ 6155.452019] [] worker_thread+0x12e/0x320 [ 6155.452019] [] ? manage_workers+0x110/0x110 [ 6155.452019] [] kthread+0xc6/0xd0 [ 6155.452019] [] kernel_thread_helper+0x4/0x10 [ 6155.452019] [] ? retint_restore_args+0x13/0x13 [ 6155.452019] [] ? __init_kthread_worker+0x70/0x70 [ 6155.452019] [] ? gs_change+0x13/0x13 This patch removes the set_cpus_allowed_ptr() call, and put the cmci rediscover jobs onto all the other cpus using system_wq. This could bring some delay for the jobs. Signed-off-by: Tang Chen Signed-off-by: Miao Xie Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce_intel.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 5f88abf07e9c..4f9a3cbfc4a3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -285,34 +285,39 @@ void cmci_clear(void) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } +static long cmci_rediscover_work_func(void *arg) +{ + int banks; + + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks); + + return 0; +} + /* * After a CPU went down cycle through all the others and rediscover * Must run in process context. */ void cmci_rediscover(int dying) { - int banks; - int cpu; - cpumask_var_t old; + int cpu, banks; if (!cmci_supported(&banks)) return; - if (!alloc_cpumask_var(&old, GFP_KERNEL)) - return; - cpumask_copy(old, ¤t->cpus_allowed); for_each_online_cpu(cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) + + if (cpu == smp_processor_id()) { + cmci_rediscover_work_func(NULL); continue; - /* Recheck banks in case CPUs don't all have the same */ - if (cmci_supported(&banks)) - cmci_discover(banks); - } + } - set_cpus_allowed_ptr(current, old); - free_cpumask_var(old); + work_on_cpu(cpu, cmci_rediscover_work_func, NULL); + } } /* -- cgit v1.2.3 From 2bbf0a1427c377350f001fbc6260995334739ad7 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Wed, 31 Oct 2012 17:20:50 +0100 Subject: x86, amd: Disable way access filter on Piledriver CPUs The Way Access Filter in recent AMD CPUs may hurt the performance of some workloads, caused by aliasing issues in the L1 cache. This patch disables it on the affected CPUs. The issue is similar to that one of last year: http://lkml.indiana.edu/hypermail/linux/kernel/1107.3/00041.html This new patch does not replace the old one, we just need another quirk for newer CPUs. The performance penalty without the patch depends on the circumstances, but is a bit less than the last year's 3%. The workloads affected would be those that access code from the same physical page under different virtual addresses, so different processes using the same libraries with ASLR or multiple instances of PIE-binaries. The code needs to be accessed simultaneously from both cores of the same compute unit. More details can be found here: http://developer.amd.com/Assets/SharedL1InstructionCacheonAMD15hCPU.pdf CPUs affected are anything with the core known as Piledriver. That includes the new parts of the AMD A-Series (aka Trinity) and the just released new CPUs of the FX-Series (aka Vishera). The model numbering is a bit odd here: FX CPUs have model 2, A-Series has model 10h, with possible extensions to 1Fh. Hence the range of model ids. Signed-off-by: Andre Przywara Link: http://lkml.kernel.org/r/1351700450-9277-1-git-send-email-osp@andrep.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/amd.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f7e98a2c0d12..1b7d1656a042 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } + /* + * The way access filter has a performance penalty on some workloads. + * Disable it on the affected CPUs. + */ + if ((c->x86 == 0x15) && + (c->x86_model >= 0x02) && (c->x86_model < 0x20)) { + u64 val; + + if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) { + val |= 0x1E; + wrmsrl_safe(0xc0011021, val); + } + } + cpu_detect_cache_sizes(c); /* Multi core CPU? */ -- cgit v1.2.3 From 279f1461432ccdec0b98c0bcbe0a8e2c0f6fdda5 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 22 Oct 2012 14:37:58 -0700 Subject: x86: apic: Use tsc deadline for oneshot when available If the TSC deadline mode is supported, LAPIC timer one-shot mode can be implemented using IA32_TSC_DEADLINE MSR. An interrupt will be generated when the TSC value equals or exceeds the value in the IA32_TSC_DEADLINE MSR. This enables us to skip the APIC calibration during boot. Also, in xapic mode, this enables us to skip the uncached apic access to re-arm the APIC timer. As this timer ticks at the high frequency TSC rate, we use the TSC_DIVISOR (32) to work with the 32-bit restrictions in the clockevent API's to avoid 64-bit divides etc (frequency is u32 and "unsigned long" in the set_next_event(), max_delta limits the next event to 32-bit for 32-bit kernel). Signed-off-by: Suresh Siddha Cc: venki@google.com Cc: len.brown@intel.com Link: http://lkml.kernel.org/r/1350941878.6017.31.camel@sbsiddha-desk.sc.intel.com Signed-off-by: Thomas Gleixner --- Documentation/kernel-parameters.txt | 4 ++ arch/x86/include/asm/msr-index.h | 2 + arch/x86/kernel/apic/apic.c | 73 +++++++++++++++++++++++++++---------- 3 files changed, 59 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9776f068306b..4aa9ca0de63c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1304,6 +1304,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. lapic [X86-32,APIC] Enable the local APIC even if BIOS disabled it. + lapic= [x86,APIC] "notscdeadline" Do not use TSC deadline + value for LAPIC timer one-shot implementation. Default + back to the programmable timer unit in the LAPIC. + lapic_timer_c2_ok [X86,APIC] trust the local apic timer in C2 power state. diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 7f0edceb7563..e400cdb2dd65 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -337,6 +337,8 @@ #define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << 38) #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << 39) +#define MSR_IA32_TSC_DEADLINE 0x000006E0 + /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b17416e72fbd..b994cc84aa7e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -90,21 +90,6 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID); -/* - * Knob to control our willingness to enable the local APIC. - * - * +1=force-enable - */ -static int force_enable_local_apic __initdata; -/* - * APIC command line parameters - */ -static int __init parse_lapic(char *arg) -{ - force_enable_local_apic = 1; - return 0; -} -early_param("lapic", parse_lapic); /* Local APIC was disabled by the BIOS and enabled by the kernel */ static int enabled_via_apicbase; @@ -133,6 +118,25 @@ static inline void imcr_apic_to_pic(void) } #endif +/* + * Knob to control our willingness to enable the local APIC. + * + * +1=force-enable + */ +static int force_enable_local_apic __initdata; +/* + * APIC command line parameters + */ +static int __init parse_lapic(char *arg) +{ + if (config_enabled(CONFIG_X86_32) && !arg) + force_enable_local_apic = 1; + else if (!strncmp(arg, "notscdeadline", 13)) + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + return 0; +} +early_param("lapic", parse_lapic); + #ifdef CONFIG_X86_64 static int apic_calibrate_pmtmr __initdata; static __init int setup_apicpmtimer(char *s) @@ -315,6 +319,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 +#define TSC_DIVISOR 32 /* * This function sets up the local APIC timer, with a timeout of @@ -333,6 +338,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) lvtt_value = LOCAL_TIMER_VECTOR; if (!oneshot) lvtt_value |= APIC_LVT_TIMER_PERIODIC; + else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE; + if (!lapic_is_integrated()) lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV); @@ -341,6 +349,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); + if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); + return; + } + /* * Divide PICLK by 16 */ @@ -453,6 +466,16 @@ static int lapic_next_event(unsigned long delta, return 0; } +static int lapic_next_deadline(unsigned long delta, + struct clock_event_device *evt) +{ + u64 tsc; + + rdtscll(tsc); + wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); + return 0; +} + /* * Setup the lapic timer in periodic or oneshot mode */ @@ -533,7 +556,15 @@ static void __cpuinit setup_APIC_timer(void) memcpy(levt, &lapic_clockevent, sizeof(*levt)); levt->cpumask = cpumask_of(smp_processor_id()); - clockevents_register_device(levt); + if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_DUMMY); + levt->set_next_event = lapic_next_deadline; + clockevents_config_and_register(levt, + (tsc_khz / TSC_DIVISOR) * 1000, + 0xF, ~0UL); + } else + clockevents_register_device(levt); } /* @@ -661,7 +692,9 @@ static int __init calibrate_APIC_clock(void) * in the clockevent structure and return. */ - if (lapic_timer_frequency) { + if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + return 0; + } else if (lapic_timer_frequency) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", lapic_timer_frequency); lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, @@ -674,6 +707,9 @@ static int __init calibrate_APIC_clock(void) return 0; } + apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" + "calibrating APIC timer ...\n"); + local_irq_disable(); /* Replace the global interrupt handler */ @@ -811,9 +847,6 @@ void __init setup_boot_APIC_clock(void) return; } - apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" - "calibrating APIC timer ...\n"); - if (calibrate_APIC_clock()) { /* No broadcast on UP ! */ if (num_possible_cpus() > 1) -- cgit v1.2.3 From 28696f434fef0efa97534b59986ad33b9c4df7f8 Mon Sep 17 00:00:00 2001 From: Salman Qazi Date: Mon, 1 Oct 2012 17:29:25 -0700 Subject: x86: Don't clobber top of pt_regs in nested NMI The nested NMI modifies the place (instruction, flags and stack) that the first NMI will iret to. However, the copy of registers modified is exactly the one that is the part of pt_regs in the first NMI. This can change the behaviour of the first NMI. In particular, Google's arch_trigger_all_cpu_backtrace handler also prints regions of memory surrounding addresses appearing in registers. This results in handled exceptions, after which nested NMIs start coming in. These nested NMIs change the value of registers in pt_regs. This can cause the original NMI handler to produce incorrect output. We solve this problem by interchanging the position of the preserved copy of the iret registers ("saved") and the copy subject to being trampled by nested NMI ("copied"). Link: http://lkml.kernel.org/r/20121002002919.27236.14388.stgit@dungbeetle.mtv.corp.google.com Signed-off-by: Salman Qazi [ Added a needed CFI_ADJUST_CFA_OFFSET ] Signed-off-by: Steven Rostedt --- arch/x86/kernel/entry_64.S | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b51b2c7ee51f..811795db4fc6 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1699,9 +1699,10 @@ nested_nmi: 1: /* Set up the interrupted NMIs stack to jump to repeat_nmi */ - leaq -6*8(%rsp), %rdx + leaq -1*8(%rsp), %rdx movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 6*8 + CFI_ADJUST_CFA_OFFSET 1*8 + leaq -10*8(%rsp), %rdx pushq_cfi $__KERNEL_DS pushq_cfi %rdx pushfq_cfi @@ -1709,8 +1710,8 @@ nested_nmi: pushq_cfi $repeat_nmi /* Put stack back */ - addq $(11*8), %rsp - CFI_ADJUST_CFA_OFFSET -11*8 + addq $(6*8), %rsp + CFI_ADJUST_CFA_OFFSET -6*8 nested_nmi_out: popq_cfi %rdx @@ -1736,18 +1737,18 @@ first_nmi: * +-------------------------+ * | NMI executing variable | * +-------------------------+ - * | Saved SS | - * | Saved Return RSP | - * | Saved RFLAGS | - * | Saved CS | - * | Saved RIP | - * +-------------------------+ * | copied SS | * | copied Return RSP | * | copied RFLAGS | * | copied CS | * | copied RIP | * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ * | pt_regs | * +-------------------------+ * @@ -1763,9 +1764,14 @@ first_nmi: /* Set the NMI executing variable on the stack. */ pushq_cfi $1 + /* + * Leave room for the "copied" frame + */ + subq $(5*8), %rsp + /* Copy the stack frame to the Saved frame */ .rept 5 - pushq_cfi 6*8(%rsp) + pushq_cfi 11*8(%rsp) .endr CFI_DEF_CFA_OFFSET SS+8-RIP @@ -1786,12 +1792,15 @@ repeat_nmi: * is benign for the non-repeat case, where 1 was pushed just above * to this very stack slot). */ - movq $1, 5*8(%rsp) + movq $1, 10*8(%rsp) /* Make another copy, this one may be modified by nested NMIs */ + addq $(10*8), %rsp + CFI_ADJUST_CFA_OFFSET -10*8 .rept 5 - pushq_cfi 4*8(%rsp) + pushq_cfi -6*8(%rsp) .endr + subq $(5*8), %rsp CFI_DEF_CFA_OFFSET SS+8-RIP end_repeat_nmi: @@ -1842,8 +1851,12 @@ nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + + /* Pop the extra iret frame */ + addq $(5*8), %rsp + /* Clear the NMI executing stack variable */ - movq $0, 10*8(%rsp) + movq $0, 5*8(%rsp) jmp irq_return CFI_ENDPROC END(nmi) -- cgit v1.2.3 From 6acf5a8c931da9d26c8dd77d784daaf07fa2bff0 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 2 Nov 2012 14:02:40 +0000 Subject: x86: hpet: Fix masking of MSI interrupts HPET_TN_FSB is not a proper mask bit; it merely toggles between MSI and legacy interrupt delivery. The proper mask bit is HPET_TN_ENABLE, so use both bits when (un)masking the interrupt. Signed-off-by: Jan Beulich Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/5093E09002000078000A60E6@nat28.tlf.novell.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/hpet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1460a5df92f7..e28670f9a589 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -434,7 +434,7 @@ void hpet_msi_unmask(struct irq_data *data) /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg |= HPET_TN_FSB; + cfg |= HPET_TN_ENABLE | HPET_TN_FSB; hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } @@ -445,7 +445,7 @@ void hpet_msi_mask(struct irq_data *data) /* mask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg &= ~HPET_TN_FSB; + cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB); hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } -- cgit v1.2.3 From 5074b85bdd3a464efe7b6de2ec163f4c07696a20 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 2 Nov 2012 14:00:29 +0000 Subject: x86: hpet: Fix inverted return value check in arch_setup_hpet_msi() setup_hpet_msi_remapped() returns a negative error indicator on error - check for this rather than for a boolean false indication, and pass on that error code rather than a meaningless "-1". Signed-off-by: Jan Beulich Cc: David Woodhouse Link: http://lkml.kernel.org/r/5093E00D02000078000A60E2@nat28.tlf.novell.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/io_apic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1817fa911024..b134f0b7ed25 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3317,8 +3317,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) int ret; if (irq_remapping_enabled) { - if (!setup_hpet_msi_remapped(irq, id)) - return -1; + ret = setup_hpet_msi_remapped(irq, id); + if (ret) + return ret; } ret = msi_compose_msg(NULL, irq, &msg, id); -- cgit v1.2.3 From 4dc316c64594d1a5ef2d61fba5ae0fe7fe18cdca Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 28 Oct 2012 17:57:30 +0100 Subject: uprobes/x86: Cleanup the single-stepping code No functional changes. Now that default arch_uprobe_enable/disable_step() helpers do nothing, x86 has no reason to reimplement them. Change arch_uprobe_*_xol() hooks to do the necessary work and remove the x86-specific hooks. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju --- arch/x86/kernel/uprobes.c | 54 +++++++++++++++++------------------------------ 1 file changed, 19 insertions(+), 35 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index aafa5557b396..c71025b67462 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -478,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) regs->ip = current->utask->xol_vaddr; pre_xol_rip_insn(auprobe, regs, autask); + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) + set_task_blockstep(current, false); + return 0; } @@ -603,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) if (auprobe->fixups & UPROBE_FIX_CALL) result = adjust_ret_addr(regs->sp, correction); + /* + * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP + * so we can get an extra SIGTRAP if we do not clear TF. We need + * to examine the opcode to make it right. + */ + if (utask->autask.saved_tf) + send_sig(SIGTRAP, current, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + return result; } @@ -647,6 +662,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.trap_nr = utask->autask.saved_trap_nr; handle_riprel_post_xol(auprobe, regs, NULL); instruction_pointer_set(regs, utask->vaddr); + + /* clear TF if it was set by us in arch_uprobe_pre_xol() */ + if (!utask->autask.saved_tf) + regs->flags &= ~X86_EFLAGS_TF; } /* @@ -676,38 +695,3 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) send_sig(SIGTRAP, current, 0); return ret; } - -void arch_uprobe_enable_step(struct arch_uprobe *auprobe) -{ - struct task_struct *task = current; - struct arch_uprobe_task *autask = &task->utask->autask; - struct pt_regs *regs = task_pt_regs(task); - - autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); - - regs->flags |= X86_EFLAGS_TF; - if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) - set_task_blockstep(task, false); -} - -void arch_uprobe_disable_step(struct arch_uprobe *auprobe) -{ - struct task_struct *task = current; - struct arch_uprobe_task *autask = &task->utask->autask; - bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); - struct pt_regs *regs = task_pt_regs(task); - /* - * The state of TIF_BLOCKSTEP was not saved so we can get an extra - * SIGTRAP if we do not clear TF. We need to examine the opcode to - * make it right. - */ - if (unlikely(trapped)) { - if (!autask->saved_tf) - regs->flags &= ~X86_EFLAGS_TF; - } else { - if (autask->saved_tf) - send_sig(SIGTRAP, task, 0); - else if (!(auprobe->fixups & UPROBE_FIX_SETF)) - regs->flags &= ~X86_EFLAGS_TF; - } -} -- cgit v1.2.3 From 193f3fcb3ab769bab4a2b9fa181eef3e5699a352 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 19 Oct 2012 10:58:13 +0200 Subject: x86: Add cpu_has_topoext Introduce cpu_has_topoext to check for AMD's CPUID topology extensions support. It indicates support for CPUID Fn8000_001D_EAX_x[N:0]-CPUID Fn8000_001E_EDX See AMD's CPUID Specification, Publication # 25481 (as of Rev. 2.34 September 2010) Signed-off-by: Andreas Herrmann Link: http://lkml.kernel.org/r/20121019085813.GD26718@alberich Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/cpufeature.h | 1 + arch/x86/kernel/cpu/amd.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 8c297aa53eef..c22a492daf57 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -311,6 +311,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) +#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f7e98a2c0d12..64e9ad4e49a0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -304,7 +304,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c80a33bc528b..732bf5cff645 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -313,7 +313,7 @@ do { \ static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && -- cgit v1.2.3 From 04a1541828ea223169eb44a336bfad8ec0dfb46a Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 19 Oct 2012 10:59:33 +0200 Subject: x86, cacheinfo: Determine number of cache leafs using CPUID 0x8000001d on AMD CPUID 0x8000001d works quite similar to Intels' CPUID function 4. Use it to determine number of cache leafs. Signed-off-by: Andreas Herrmann Link: http://lkml.kernel.org/r/20121019085933.GE26718@alberich Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/amd.c | 7 +------ arch/x86/kernel/cpu/intel_cacheinfo.c | 28 +++++++++++++++++++++++----- 3 files changed, 25 insertions(+), 12 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ad1fc8511674..db0d8c32090c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -187,7 +187,7 @@ extern void print_cpu_info(struct cpuinfo_x86 *); void print_cpu_msr(struct cpuinfo_x86 *); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); -extern unsigned short num_cache_leaves; +extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void detect_extended_topology(struct cpuinfo_x86 *c); extern void detect_ht(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 64e9ad4e49a0..a8538e6d2ff2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -643,12 +643,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) detect_ht(c); #endif - if (c->extended_cpuid_level >= 0x80000006) { - if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; - else - num_cache_leaves = 3; - } + init_amd_cacheinfo(c); if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 93c5451bdd52..8ce7a83252f9 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -557,21 +557,39 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int __cpuinit find_num_cache_leaves(void) +static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c) { - unsigned int eax, ebx, ecx, edx; + unsigned int eax, ebx, ecx, edx, op; union _cpuid4_leaf_eax cache_eax; int i = -1; + if (c->x86_vendor == X86_VENDOR_AMD) + op = 0x8000001d; + else + op = 4; + do { ++i; - /* Do cpuid(4) loop to find out num_cache_leaves */ - cpuid_count(4, i, &eax, &ebx, &ecx, &edx); + /* Do cpuid(op) loop to find out num_cache_leaves */ + cpuid_count(op, i, &eax, &ebx, &ecx, &edx); cache_eax.full = eax; } while (cache_eax.split.type != CACHE_TYPE_NULL); return i; } +void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c) +{ + + if (cpu_has_topoext) { + num_cache_leaves = find_num_cache_leaves(c); + } else if (c->extended_cpuid_level >= 0x80000006) { + if (cpuid_edx(0x80000006) & 0xf000) + num_cache_leaves = 4; + else + num_cache_leaves = 3; + } +} + unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ @@ -588,7 +606,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (is_initialized == 0) { /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(); + num_cache_leaves = find_num_cache_leaves(c); is_initialized++; } -- cgit v1.2.3 From 2e8458dfe4202df75543402c7343b8f94de4101e Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 19 Oct 2012 11:00:49 +0200 Subject: x86, cacheinfo: Make use of CPUID 0x8000001d for cache information on AMD Rely on CPUID 0x8000001d for cache information when AMD CPUID topology extensions are available. Signed-off-by: Andreas Herrmann Link: http://lkml.kernel.org/r/20121019090049.GF26718@alberich Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel_cacheinfo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 8ce7a83252f9..cd2e1ccce591 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -538,7 +538,11 @@ __cpuinit cpuid4_cache_lookup_regs(int index, unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - amd_cpuid4(index, &eax, &ebx, &ecx); + if (cpu_has_topoext) + cpuid_count(0x8000001d, index, &eax.full, + &ebx.full, &ecx.full, &edx); + else + amd_cpuid4(index, &eax, &ebx, &ecx); amd_init_l3_cache(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); -- cgit v1.2.3 From 27d3a8a26ada7660116fdd6830096008c063ee96 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 19 Oct 2012 11:02:09 +0200 Subject: x86, cacheinfo: Base cache sharing info on CPUID 0x8000001d on AMD The patch is based on a patch submitted by Hans Rosenfeld. See http://marc.info/?l=linux-kernel&m=133908777200931 Note that CPUID Fn8000_001D_EAX slightly differs to Intel's CPUID function 4. Bits 14-25 contain NumSharingCache. Actual number of cores sharing this cache. SW to add value of one to get result. The corresponding bits on Intel are defined as "maximum number of threads sharing this cache" (with a "plus 1" encoding). Thus a different method to determine which cores are sharing a cache level has to be used. Signed-off-by: Andreas Herrmann Link: http://lkml.kernel.org/r/20121019090209.GG26718@alberich Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel_cacheinfo.c | 41 +++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index cd2e1ccce591..fe9edec6698a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -750,37 +750,50 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf; - int ret, i, sibling; - struct cpuinfo_x86 *c = &cpu_data(cpu); + int i, sibling; - ret = 0; - if (index == 3) { - ret = 1; - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + if (cpu_has_topoext) { + unsigned int apicid, nshared, first, last; + + if (!per_cpu(ici_cpuid4_info, cpu)) + return 0; + + this_leaf = CPUID4_INFO_IDX(cpu, index); + nshared = this_leaf->base.eax.split.num_threads_sharing + 1; + apicid = cpu_data(cpu).apicid; + first = apicid - (apicid % nshared); + last = first + nshared - 1; + + for_each_online_cpu(i) { + apicid = cpu_data(i).apicid; + if ((apicid < first) || (apicid > last)) + continue; if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) + + for_each_online_cpu(sibling) { + apicid = cpu_data(sibling).apicid; + if ((apicid < first) || (apicid > last)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { - ret = 1; - for_each_cpu(i, cpu_sibling_mask(cpu)) { + } else if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { if (!cpu_online(sibling)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } + } else + return 0; - return ret; + return 1; } static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) -- cgit v1.2.3 From 8cbd9cc6254065c97c4bac42daa55ba1abe73a8e Mon Sep 17 00:00:00 2001 From: David Sharp Date: Tue, 13 Nov 2012 12:18:21 -0800 Subject: tracing,x86: Add a TSC trace_clock In order to promote interoperability between userspace tracers and ftrace, add a trace_clock that reports raw TSC values which will then be recorded in the ring buffer. Userspace tracers that also record TSCs are then on exactly the same time base as the kernel and events can be unambiguously interlaced. Tested: Enabled a tracepoint and the "tsc" trace_clock and saw very large timestamp values. v2: Move arch-specific bits out of generic code. v3: Rename "x86-tsc", cleanups v7: Generic arch bits in Kbuild. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-1-git-send-email-dhsharp@google.com Acked-by: Ingo Molnar Cc: Masami Hiramatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: David Sharp Signed-off-by: Steven Rostedt --- arch/alpha/include/asm/Kbuild | 1 + arch/arm/include/asm/Kbuild | 1 + arch/arm64/include/asm/Kbuild | 1 + arch/avr32/include/asm/Kbuild | 1 + arch/blackfin/include/asm/Kbuild | 1 + arch/c6x/include/asm/Kbuild | 1 + arch/cris/include/asm/Kbuild | 1 + arch/frv/include/asm/Kbuild | 1 + arch/h8300/include/asm/Kbuild | 1 + arch/hexagon/include/asm/Kbuild | 1 + arch/ia64/include/asm/Kbuild | 1 + arch/m32r/include/asm/Kbuild | 1 + arch/m68k/include/asm/Kbuild | 1 + arch/microblaze/include/asm/Kbuild | 1 + arch/mips/include/asm/Kbuild | 1 + arch/mn10300/include/asm/Kbuild | 1 + arch/openrisc/include/asm/Kbuild | 1 + arch/parisc/include/asm/Kbuild | 1 + arch/powerpc/include/asm/Kbuild | 1 + arch/s390/include/asm/Kbuild | 1 + arch/score/include/asm/Kbuild | 1 + arch/sh/include/asm/Kbuild | 1 + arch/sparc/include/asm/Kbuild | 1 + arch/tile/include/asm/Kbuild | 1 + arch/um/include/asm/Kbuild | 1 + arch/unicore32/include/asm/Kbuild | 1 + arch/x86/include/asm/trace_clock.h | 20 ++++++++++++++++++++ arch/x86/kernel/Makefile | 1 + arch/x86/kernel/trace_clock.c | 21 +++++++++++++++++++++ arch/xtensa/include/asm/Kbuild | 1 + include/asm-generic/trace_clock.h | 16 ++++++++++++++++ include/linux/trace_clock.h | 2 ++ kernel/trace/trace.c | 1 + 33 files changed, 88 insertions(+) create mode 100644 arch/x86/include/asm/trace_clock.h create mode 100644 arch/x86/kernel/trace_clock.c create mode 100644 include/asm-generic/trace_clock.h (limited to 'arch/x86/kernel') diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 64ffc9e9e548..dcfabb9f05a0 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -11,3 +11,4 @@ header-y += reg.h header-y += regdef.h header-y += sysinfo.h generic-y += exec.h +generic-y += trace_clock.h diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index f70ae175a3d6..514e398f1a07 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -31,5 +31,6 @@ generic-y += sockios.h generic-y += termbits.h generic-y += termios.h generic-y += timex.h +generic-y += trace_clock.h generic-y += types.h generic-y += unaligned.h diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index a581a2205938..6e9ca462127f 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -43,6 +43,7 @@ generic-y += swab.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += unaligned.h generic-y += user.h diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index 4807ded352c5..4dd4f78d3dcc 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -1,3 +1,4 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += trace_clock.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 5a0625aad6a0..27d70759474c 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -38,6 +38,7 @@ generic-y += statfs.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 112a496d8355..eae7b5963e86 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -49,6 +49,7 @@ generic-y += termbits.h generic-y += termios.h generic-y += tlbflush.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += user.h diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index 6d43a951b5ec..15a122c3767c 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -11,3 +11,4 @@ header-y += sync_serial.h generic-y += clkdev.h generic-y += exec.h generic-y += module.h +generic-y += trace_clock.h diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index 4a159da23633..c5d767028306 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -1,3 +1,4 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += trace_clock.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 50bbf387b2f8..4bc8ae73e08a 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm generic-y += clkdev.h generic-y += exec.h generic-y += module.h +generic-y += trace_clock.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 3bfa9b30f448..bdb54ceb53bc 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -48,6 +48,7 @@ generic-y += stat.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index dd02f09b6eda..05b03ecd7933 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += clkdev.h generic-y += exec.h generic-y += kvm_para.h +generic-y += trace_clock.h diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index 50bbf387b2f8..4bc8ae73e08a 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm generic-y += clkdev.h generic-y += exec.h generic-y += module.h +generic-y += trace_clock.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 88fa3ac86fae..7f1949c0e089 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -24,6 +24,7 @@ generic-y += sections.h generic-y += siginfo.h generic-y += statfs.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 8653072d7e9f..2957fcc71764 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm header-y += elf.h generic-y += clkdev.h generic-y += exec.h +generic-y += trace_clock.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 533053d12ced..9b54b7a403d4 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -1 +1,2 @@ # MIPS headers +generic-y += trace_clock.h diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index 4a159da23633..c5d767028306 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -1,3 +1,4 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += trace_clock.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 78de6805268d..8971026e1c63 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -60,6 +60,7 @@ generic-y += swab.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += user.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index bac8debecffb..ff4c9faed546 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -3,3 +3,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \ segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \ div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \ poll.h xor.h clkdev.h exec.h +generic-y += trace_clock.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index a4fe15e33c6f..2d62b484b3fc 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += clkdev.h generic-y += rwsem.h +generic-y += trace_clock.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 0633dc6d254d..f313f9cbcf44 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,3 +1,4 @@ generic-y += clkdev.h +generic-y += trace_clock.h diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index ec697aeefd05..16e41fe1a419 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm header-y += generic-y += clkdev.h +generic-y += trace_clock.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 29f83beeef7a..280bea9e5e2b 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -31,5 +31,6 @@ generic-y += socket.h generic-y += statfs.h generic-y += termbits.h generic-y += termios.h +generic-y += trace_clock.h generic-y += ucontext.h generic-y += xor.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 645a58da0e86..e26d430ce2fd 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -8,4 +8,5 @@ generic-y += local64.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += trace_clock.h generic-y += word-at-a-time.h diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 6948015e08a2..b17b9b8e53cd 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -34,5 +34,6 @@ generic-y += sockios.h generic-y += statfs.h generic-y += termbits.h generic-y += termios.h +generic-y += trace_clock.h generic-y += types.h generic-y += xor.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 0f6e7b328265..b30f34a79882 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h generic-y += switch_to.h clkdev.h +generic-y += trace_clock.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index c910c9857e11..7be503e45695 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -54,6 +54,7 @@ generic-y += syscalls.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h new file mode 100644 index 000000000000..5c1652728b6d --- /dev/null +++ b/arch/x86/include/asm/trace_clock.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_TRACE_CLOCK_H +#define _ASM_X86_TRACE_CLOCK_H + +#include +#include + +#ifdef CONFIG_X86_TSC + +extern u64 notrace trace_clock_x86_tsc(void); + +# define ARCH_TRACE_CLOCKS \ + { trace_clock_x86_tsc, "x86-tsc" }, + +#else /* !CONFIG_X86_TSC */ + +#define ARCH_TRACE_CLOCKS + +#endif + +#endif /* _ASM_X86_TRACE_CLOCK_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9fd5eed3f8f5..34e923a53762 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c new file mode 100644 index 000000000000..25b993729f9b --- /dev/null +++ b/arch/x86/kernel/trace_clock.c @@ -0,0 +1,21 @@ +/* + * X86 trace clocks + */ +#include +#include +#include + +/* + * trace_clock_x86_tsc(): A clock that is just the cycle counter. + * + * Unlike the other clocks, this is not in nanoseconds. + */ +u64 notrace trace_clock_x86_tsc(void) +{ + u64 ret; + + rdtsc_barrier(); + rdtscll(ret); + + return ret; +} diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 6d1302789995..095f0a2244f7 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -25,4 +25,5 @@ generic-y += siginfo.h generic-y += statfs.h generic-y += termios.h generic-y += topology.h +generic-y += trace_clock.h generic-y += xor.h diff --git a/include/asm-generic/trace_clock.h b/include/asm-generic/trace_clock.h new file mode 100644 index 000000000000..6726f1bafb5e --- /dev/null +++ b/include/asm-generic/trace_clock.h @@ -0,0 +1,16 @@ +#ifndef _ASM_GENERIC_TRACE_CLOCK_H +#define _ASM_GENERIC_TRACE_CLOCK_H +/* + * Arch-specific trace clocks. + */ + +/* + * Additional trace clocks added to the trace_clocks + * array in kernel/trace/trace.c + * None if the architecture has not defined it. + */ +#ifndef ARCH_TRACE_CLOCKS +# define ARCH_TRACE_CLOCKS +#endif + +#endif /* _ASM_GENERIC_TRACE_CLOCK_H */ diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index 4eb490237d4c..d563f37e1a1d 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -12,6 +12,8 @@ #include #include +#include + extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); extern u64 notrace trace_clock_global(void); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c1434b5ce4d1..0d20620c0d27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -488,6 +488,7 @@ static struct { { trace_clock_local, "local" }, { trace_clock_global, "global" }, { trace_clock_counter, "counter" }, + ARCH_TRACE_CLOCKS }; int trace_clock_id; -- cgit v1.2.3 From 4d25031a81d3cd32edc00de6596db76cc4010685 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:40 -0800 Subject: x86, topology: Don't offline CPU0 if any PIC irq can not be migrated out of it If CONFIG_BOOTPARAM_HOTPLUG_CPU is turned on, CPU0 hotplug feature is enabled by default. If CONFIG_BOOTPARAM_HOTPLUG_CPU is not turned on, CPU0 hotplug feature is not enabled by default. The kernel parameter cpu0_hotplug can enable CPU0 hotplug feature at boot. Currently the feature is supported on Intel platforms only. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-4-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/topology.c | 50 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 43 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 76ee97709a00..0e7b4a7a7fb8 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -30,23 +30,59 @@ #include #include #include +#include #include static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU + +#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0 +static int cpu0_hotpluggable = 1; +#else +static int cpu0_hotpluggable; +static int __init enable_cpu0_hotplug(char *str) +{ + cpu0_hotpluggable = 1; + return 1; +} + +__setup("cpu0_hotplug", enable_cpu0_hotplug); +#endif + int __ref arch_register_cpu(int num) { + struct cpuinfo_x86 *c = &cpu_data(num); + + /* + * Currently CPU0 is only hotpluggable on Intel platforms. Other + * vendors can add hotplug support later. + */ + if (c->x86_vendor != X86_VENDOR_INTEL) + cpu0_hotpluggable = 0; + /* - * CPU0 cannot be offlined due to several - * restrictions and assumptions in kernel. This basically - * doesn't add a control file, one cannot attempt to offline - * BSP. + * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate + * depends on BSP. PIC interrupts depend on BSP. * - * Also certain PCI quirks require not to enable hotplug control - * for all CPU's. + * If the BSP depencies are under control, one can tell kernel to + * enable BSP hotplug. This basically adds a control file and + * one can attempt to offline BSP. */ - if (num) + if (num == 0 && cpu0_hotpluggable) { + unsigned int irq; + /* + * We won't take down the boot processor on i386 if some + * interrupts only are able to be serviced by the BSP in PIC. + */ + for_each_active_irq(irq) { + if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) { + cpu0_hotpluggable = 0; + break; + } + } + } + if (num || cpu0_hotpluggable) per_cpu(cpu_devices, num).cpu.hotpluggable = 1; return register_cpu(&per_cpu(cpu_devices, num).cpu, num); -- cgit v1.2.3 From 30106c174311b8cfaaa3186c7f6f9c36c62d17da Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:41 -0800 Subject: x86, hotplug: Support functions for CPU0 online/offline Add smp_store_boot_cpu_info() to store cpu info for BSP during boot time. Now smp_store_cpu_info() stores cpu info for bringing up BSP or AP after it's offline. Continue to online CPU0 in native_cpu_up(). Continue to offline CPU0 in native_cpu_disable(). Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-5-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/smpboot.c | 38 ++++++++++++++++++-------------------- 2 files changed, 19 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4f19a1526037..b073aaea747c 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -166,6 +166,7 @@ void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); +void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c80a33bc528b..c297907f3c75 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -125,8 +125,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; /* - * Report back to the Boot Processor. - * Running on AP. + * Report back to the Boot Processor during boot time or to the caller processor + * during CPU online. */ static void __cpuinit smp_callin(void) { @@ -279,19 +279,30 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } +void __init smp_store_boot_cpu_info(void) +{ + int id = 0; /* CPU 0 */ + struct cpuinfo_x86 *c = &cpu_data(id); + + *c = boot_cpu_data; + c->cpu_index = id; +} + /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU */ - void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); *c = boot_cpu_data; c->cpu_index = id; - if (id != 0) - identify_secondary_cpu(c); + /* + * During boot time, CPU0 has this setup already. Save the info when + * bringing up AP or offlined CPU0. + */ + identify_secondary_cpu(c); } static bool __cpuinit @@ -795,7 +806,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || + if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) || !apic->apic_id_valid(apicid)) { pr_err("%s: bad cpu %d\n", __func__, cpu); @@ -990,7 +1001,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* * Setup boot CPU information */ - smp_store_cpu_info(0); /* Final full version of the data */ + smp_store_boot_cpu_info(); /* Final full version of the data */ cpumask_copy(cpu_callin_mask, cpumask_of(0)); mb(); @@ -1214,19 +1225,6 @@ void cpu_disable_common(void) int native_cpu_disable(void) { - int cpu = smp_processor_id(); - - /* - * Perhaps use cpufreq to drop frequency, but that could go - * into generic code. - * - * We won't take down the boot processor on i386 due to some - * interrupts only being able to be serviced by the BSP. - * Especially so if we're not using an IOAPIC -zwane - */ - if (cpu == 0) - return -EBUSY; - clear_local_APIC(); cpu_disable_common(); -- cgit v1.2.3 From 42e78e9719aa0c76711e2731b19c90fe5ae05278 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:44 -0800 Subject: x86-64, hotplug: Add start_cpu0() entry point to head_64.S start_cpu0() is defined in head_64.S for 64-bit. The function sets up stack and jumps to start_secondary() for CPU0 wake up. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-8-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_64.S | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 94bf9cc2c7ee..980053c4b9cc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -252,6 +252,22 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movq stack_start(%rip),%rsp + movq initial_code(%rip),%rax + pushq $0 # fake return address to stop unwinder + pushq $__KERNEL_CS # set correct cs + pushq %rax # target address in negative space + lretq +ENDPROC(start_cpu0) +#endif + /* SMP bootup changes these two */ __REFDATA .align 8 -- cgit v1.2.3 From 3e2a0cc3cdc19e0518ae87583add40ea1bf55b67 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:45 -0800 Subject: x86-32, hotplug: Add start_cpu0() entry point to head_32.S start_cpu0() is defined in head_32.S for 32-bit. The function sets up stack and jumps to start_secondary() for CPU0 wake up. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-9-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 957a47aec64e..a013e7390ab5 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -266,6 +266,19 @@ num_subarch_entries = (. - subarch_entries) / 4 jmp default_entry #endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movl stack_start, %ecx + movl %ecx, %esp + jmp *(initial_code) +ENDPROC(start_cpu0) +#endif + /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but -- cgit v1.2.3 From 1bad2f19f7f79d1ec9e6c48168fd7ce8dc1c305f Mon Sep 17 00:00:00 2001 From: Kristen Carlson Accardi Date: Fri, 26 Oct 2012 13:39:15 +0200 Subject: ACPI / Sleep: add acpi_sleep=nonvs_s3 parameter The ACPI specificiation would like us to save NVS at hibernation time, but makes no mention of saving NVS over S3. Not all versions of Windows do this either, and it is clear that not all machines need NVS saved/restored over S3. Allow the user to improve their suspend/resume time by disabling the NVS save/restore at S3 time, but continue to do the NVS save/restore for S4 as specified. Signed-off-by: Kristen Carlson Accardi Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/acpi/sleep.c | 2 ++ drivers/acpi/sleep.c | 17 ++++++++++++++++- include/linux/acpi.h | 1 + 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 11676cf65aee..d5e0d717005a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -101,6 +101,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); + if (strncmp(str, "nonvs_s3", 8) == 0) + acpi_nvs_nosave_s3(); if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index fdcdbb652915..8640782944cc 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -97,6 +97,21 @@ void __init acpi_nvs_nosave(void) nvs_nosave = true; } +/* + * The ACPI specification wants us to save NVS memory regions during hibernation + * but says nothing about saving NVS during S3. Not all versions of Windows + * save NVS on S3 suspend either, and it is clear that not all systems need + * NVS to be saved at S3 time. To improve suspend/resume time, allow the + * user to disable saving NVS on S3 if their system does not require it, but + * continue to save/restore NVS for S4 as specified. + */ +static bool nvs_nosave_s3; + +void __init acpi_nvs_nosave_s3(void) +{ + nvs_nosave_s3 = true; +} + /* * ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the * user to request that behavior by using the 'acpi_old_suspend_ordering' @@ -243,7 +258,7 @@ static int acpi_suspend_begin(suspend_state_t pm_state) u32 acpi_state = acpi_suspend_states[pm_state]; int error = 0; - error = nvs_nosave ? 0 : suspend_nvs_alloc(); + error = (nvs_nosave || nvs_nosave_s3) ? 0 : suspend_nvs_alloc(); if (error) return error; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 90be98981102..3cf93491125c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -261,6 +261,7 @@ int acpi_resources_are_enforced(void); void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); +void __init acpi_nvs_nosave_s3(void); #endif /* CONFIG_PM_SLEEP */ struct acpi_osc_context { -- cgit v1.2.3 From 35e92b78c1d327b1624e94d1c9c65ea7065d6b95 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 31 Oct 2012 22:44:48 +0100 Subject: ACPI / x86: Export acpi_[un]register_gsi() These functions might be called from modules as well so make sure they are exported. In addition, implement empty version of acpi_unregister_gsi() and remove the one from pci_irq.c. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg Acked-by: Greg Kroah-Hartman Acked-by: H. Peter Anvin Acked-by: Tony Luck Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/acpi/boot.c | 6 ++++++ drivers/acpi/pci_irq.c | 5 ----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e651f7a589ac..e48cafcf92ae 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -574,6 +574,12 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) return irq; } +EXPORT_SYMBOL_GPL(acpi_register_gsi); + +void acpi_unregister_gsi(u32 gsi) +{ +} +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); void __init acpi_set_irq_model_pic(void) { diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 0eefa12e648c..1be25a590dce 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -495,11 +495,6 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } -/* FIXME: implement x86/x86_64 version */ -void __attribute__ ((weak)) acpi_unregister_gsi(u32 i) -{ -} - void acpi_pci_irq_disable(struct pci_dev *dev) { struct acpi_prt_entry *entry; -- cgit v1.2.3 From e1c467e69040c3be68959332959c07fb3d818e87 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Wed, 14 Nov 2012 04:36:53 -0800 Subject: x86, hotplug: Wake up CPU0 via NMI instead of INIT, SIPI, SIPI Instead of waiting for STARTUP after INITs, BSP will execute the BIOS boot-strap code which is not a desired behavior for waking up BSP. To avoid the boot-strap code, wake up CPU0 by NMI instead. This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined (i.e. physically hot removed and then hot added), NMI won't wake it up. We'll change this code in the future to wake up hard offlined CPU0 if real platform and request are available. AP is still waken up as before by INIT, SIPI, SIPI sequence. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352896613-25957-1-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/cpu.h | 1 + arch/x86/kernel/smpboot.c | 111 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 105 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 4564c8e28a33..a1195726e8c2 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -28,6 +28,7 @@ struct x86_cpu { #ifdef CONFIG_HOTPLUG_CPU extern int arch_register_cpu(int num); extern void arch_unregister_cpu(int); +extern void __cpuinit start_cpu0(void); #endif DECLARE_PER_CPU(int, cpu_state); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c297907f3c75..ef53e667e051 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -138,15 +138,17 @@ static void __cpuinit smp_callin(void) * we may get here before an INIT-deassert IPI reaches * our local APIC. We have to wait for the IPI or we'll * lock up on an APIC access. + * + * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. */ - if (apic->wait_for_init_deassert) + cpuid = smp_processor_id(); + if (apic->wait_for_init_deassert && cpuid != 0) apic->wait_for_init_deassert(&init_deasserted); /* * (This works even if the APIC is not enabled.) */ phys_id = read_apic_id(); - cpuid = smp_processor_id(); if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, phys_id, cpuid); @@ -228,6 +230,8 @@ static void __cpuinit smp_callin(void) cpumask_set_cpu(cpuid, cpu_callin_mask); } +static int cpu0_logical_apicid; +static int enable_start_cpu0; /* * Activate a secondary processor. */ @@ -243,6 +247,8 @@ notrace static void __cpuinit start_secondary(void *unused) preempt_disable(); smp_callin(); + enable_start_cpu0 = 0; + #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); @@ -492,7 +498,7 @@ void __inquire_remote_apic(int apicid) * won't ... remember to clear down the APIC, etc later. */ int __cpuinit -wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) +wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; int maxlvt; @@ -500,7 +506,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) /* Target chip */ /* Boot on the stack */ /* Kick the second */ - apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid); + apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -660,6 +666,63 @@ static void __cpuinit announce_cpu(int cpu, int apicid) node, cpu, apicid); } +static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) +{ + int cpu; + + cpu = smp_processor_id(); + if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0) + return NMI_HANDLED; + + return NMI_DONE; +} + +/* + * Wake up AP by INIT, INIT, STARTUP sequence. + * + * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS + * boot-strap code which is not a desired behavior for waking up BSP. To + * void the boot-strap code, wake up CPU0 by NMI instead. + * + * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined + * (i.e. physically hot removed and then hot added), NMI won't wake it up. + * We'll change this code in the future to wake up hard offlined CPU0 if + * real platform and request are available. + */ +static int __cpuinit +wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, + int *cpu0_nmi_registered) +{ + int id; + int boot_error; + + /* + * Wake up AP by INIT, INIT, STARTUP sequence. + */ + if (cpu) + return wakeup_secondary_cpu_via_init(apicid, start_ip); + + /* + * Wake up BSP by nmi. + * + * Register a NMI handler to help wake up CPU0. + */ + boot_error = register_nmi_handler(NMI_LOCAL, + wakeup_cpu0_nmi, 0, "wake_cpu0"); + + if (!boot_error) { + enable_start_cpu0 = 1; + *cpu0_nmi_registered = 1; + if (apic->dest_logical == APIC_DEST_LOGICAL) + id = cpu0_logical_apicid; + else + id = apicid; + boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); + } + + return boot_error; +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -675,6 +738,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; + int cpu0_nmi_registered = 0; /* Just in case we booted with a single CPU. */ alternatives_enable_smp(); @@ -722,13 +786,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) } /* - * Kick the secondary CPU. Use the method in the APIC driver - * if it's defined - or use an INIT boot APIC message otherwise: + * Wake up a CPU in difference cases: + * - Use the method in the APIC driver if it's defined + * Otherwise, + * - Use an INIT boot APIC message for APs or NMI for BSP. */ if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else - boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); + boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, + &cpu0_nmi_registered); if (!boot_error) { /* @@ -793,6 +860,13 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + return boot_error; } @@ -1037,6 +1111,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) */ setup_local_APIC(); + if (x2apic_mode) + cpu0_logical_apicid = apic_read(APIC_LDR); + else + cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + /* * Enable IO APIC before setting up error vector */ @@ -1264,6 +1343,14 @@ void play_dead_common(void) local_irq_disable(); } +static bool wakeup_cpu0(void) +{ + if (smp_processor_id() == 0 && enable_start_cpu0) + return true; + + return false; +} + /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. @@ -1327,6 +1414,11 @@ static inline void mwait_play_dead(void) __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } @@ -1337,6 +1429,11 @@ static inline void hlt_play_dead(void) while (1) { native_halt(); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } -- cgit v1.2.3 From 27fd185f3d9e83c64b7a596881d7751a638c9683 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:47 -0800 Subject: x86, hotplug: During CPU0 online, enable x2apic, set_numa_node. Previously these functions were not run on the BSP (CPU 0, the boot processor) since the boot processor init would only be executed before this functionality was initialized. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-11-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 7505f7b13e71..ca165ac6793b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1237,7 +1237,7 @@ void __cpuinit cpu_init(void) oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA - if (cpu != 0 && this_cpu_read(numa_node) == 0 && + if (this_cpu_read(numa_node) == 0 && early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif @@ -1269,8 +1269,7 @@ void __cpuinit cpu_init(void) barrier(); x86_configure_nx(); - if (cpu != 0) - enable_x2apic(); + enable_x2apic(); /* * set up and load the per-CPU TSS -- cgit v1.2.3 From 30242aa6023b71325c6b8addac06faf544a85fd0 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:48 -0800 Subject: x86, hotplug: The first online processor saves the MTRR state Ask the first online CPU to save mtrr instead of asking BSP. BSP could be offline when mtrr_save_state() is called. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-12-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mtrr/main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6b96110bb0c3..e4c1a4184531 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -695,11 +695,16 @@ void mtrr_ap_init(void) } /** - * Save current fixed-range MTRR state of the BSP + * Save current fixed-range MTRR state of the first cpu in cpu_online_mask. */ void mtrr_save_state(void) { - smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1); + int first_cpu; + + get_online_cpus(); + first_cpu = cpumask_first(cpu_online_mask); + smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); + put_online_cpus(); } void set_mtrr_aps_delayed_init(void) -- cgit v1.2.3 From 8d966a04107e56993a051cd41ead0b4f23ba2414 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:49 -0800 Subject: x86, hotplug: Handle retrigger irq by the first available CPU The first cpu in irq cfg->domain is likely to be CPU 0 and may not be available when CPU 0 is offline. Instead of using CPU 0 to handle retriggered irq, we use first available CPU which is online and in this irq's domain. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-13-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/io_apic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1817fa911024..f78fc2b4deb0 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2199,9 +2199,11 @@ static int ioapic_retrigger_irq(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; unsigned long flags; + int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); + cpu = cpumask_first_and(cfg->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; -- cgit v1.2.3 From 6f5298c2139b06925037490367906f3d73955b86 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:50 -0800 Subject: x86/i387.c: Initialize thread xstate only on CPU0 only once init_thread_xstate() is only called once to avoid overriding xstate_size during boot time or during CPU hotplug. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-14-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/i387.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 675a05012449..245a71db401a 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -175,7 +175,11 @@ void __cpuinit fpu_init(void) cr0 |= X86_CR0_EM; write_cr0(cr0); - if (!smp_processor_id()) + /* + * init_thread_xstate is only called once to avoid overriding + * xstate_size during boot time or during CPU hotplug. + */ + if (xstate_size == 0) init_thread_xstate(); mxcsr_feature_mask_init(); -- cgit v1.2.3 From a71c8bc5dfefbbf80ef90739791554ef7ea4401b Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 13 Nov 2012 11:32:51 -0800 Subject: x86, topology: Debug CPU0 hotplug CONFIG_DEBUG_HOTPLUG_CPU0 is for debugging the CPU0 hotplug feature. The switch offlines CPU0 as soon as possible and boots userspace up with CPU0 offlined. User can online CPU0 back after boot time. The default value of the switch is off. To debug CPU0 hotplug, you need to enable CPU0 offline/online feature by either turning on CONFIG_BOOTPARAM_HOTPLUG_CPU0 during compilation or giving cpu0_hotplug kernel parameter at boot. It's safe and early place to take down CPU0 after all hotplug notifiers are installed and SMP is booted. Please note that some applications or drivers, e.g. some versions of udevd, during boot time may put CPU0 online again in this CPU0 hotplug debug mode. In this debug mode, setup_local_APIC() may report a warning on max_loops<=0 when CPU0 is onlined back after boot time. This is because pending interrupt in IRR can not move to ISR. The warning is not CPU0 specfic and it can happen on other CPUs as well. It is harmless except the first CPU0 online takes a bit longer time. And so this debug mode is useful to expose this issue. I'll send a seperate patch to fix this generic warning issue. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1352835171-3958-15-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 15 ++++++++++++++ arch/x86/include/asm/cpu.h | 3 +++ arch/x86/kernel/topology.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++ arch/x86/power/cpu.c | 38 ++++++++++++++++++++++++++++++++++ 4 files changed, 107 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 036e89ab470c..b6cfa5f62529 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1727,6 +1727,21 @@ config BOOTPARAM_HOTPLUG_CPU0 You still can enable the CPU0 hotplug feature at boot by kernel parameter cpu0_hotplug. +config DEBUG_HOTPLUG_CPU0 + def_bool n + prompt "Debug CPU0 hotplug" + depends on HOTPLUG_CPU && EXPERIMENTAL + ---help--- + Enabling this option offlines CPU0 (if CPU0 can be offlined) as + soon as possible and boots up userspace with CPU0 offlined. User + can online CPU0 back after boot time. + + To debug CPU0 hotplug, you need to enable CPU0 offline/online + feature by either turning on CONFIG_BOOTPARAM_HOTPLUG_CPU0 during + compilation or giving cpu0_hotplug kernel parameter at boot. + + If unsure, say N. + config COMPAT_VDSO def_bool y prompt "Compat VDSO support" diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index a1195726e8c2..5f9a1243190e 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -29,6 +29,9 @@ struct x86_cpu { extern int arch_register_cpu(int num); extern void arch_unregister_cpu(int); extern void __cpuinit start_cpu0(void); +#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 +extern int _debug_hotplug_cpu(int cpu, int action); +#endif #endif DECLARE_PER_CPU(int, cpu_state); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 0e7b4a7a7fb8..6e60b5fe2244 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -50,6 +50,57 @@ static int __init enable_cpu0_hotplug(char *str) __setup("cpu0_hotplug", enable_cpu0_hotplug); #endif +#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 +/* + * This function offlines a CPU as early as possible and allows userspace to + * boot up without the CPU. The CPU can be onlined back by user after boot. + * + * This is only called for debugging CPU offline/online feature. + */ +int __ref _debug_hotplug_cpu(int cpu, int action) +{ + struct device *dev = get_cpu_device(cpu); + int ret; + + if (!cpu_is_hotpluggable(cpu)) + return -EINVAL; + + cpu_hotplug_driver_lock(); + + switch (action) { + case 0: + ret = cpu_down(cpu); + if (!ret) { + pr_info("CPU %u is now offline\n", cpu); + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + } else + pr_debug("Can't offline CPU%d.\n", cpu); + break; + case 1: + ret = cpu_up(cpu); + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + else + pr_debug("Can't online CPU%d.\n", cpu); + break; + default: + ret = -EINVAL; + } + + cpu_hotplug_driver_unlock(); + + return ret; +} + +static int __init debug_hotplug_cpu(void) +{ + _debug_hotplug_cpu(0, 0); + return 0; +} + +late_initcall_sync(debug_hotplug_cpu); +#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ + int __ref arch_register_cpu(int num) { struct cpuinfo_x86 *c = &cpu_data(num); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index adde77588e25..120cee1c3f8d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -21,6 +21,7 @@ #include #include #include /* pcntxt_mask */ +#include #ifdef CONFIG_X86_32 static struct saved_context saved_context; @@ -263,6 +264,43 @@ static int bsp_pm_callback(struct notifier_block *nb, unsigned long action, case PM_HIBERNATION_PREPARE: ret = bsp_check(); break; +#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 + case PM_RESTORE_PREPARE: + /* + * When system resumes from hibernation, online CPU0 because + * 1. it's required for resume and + * 2. the CPU was online before hibernation + */ + if (!cpu_online(0)) + _debug_hotplug_cpu(0, 1); + break; + case PM_POST_RESTORE: + /* + * When a resume really happens, this code won't be called. + * + * This code is called only when user space hibernation software + * prepares for snapshot device during boot time. So we just + * call _debug_hotplug_cpu() to restore to CPU0's state prior to + * preparing the snapshot device. + * + * This works for normal boot case in our CPU0 hotplug debug + * mode, i.e. CPU0 is offline and user mode hibernation + * software initializes during boot time. + * + * If CPU0 is online and user application accesses snapshot + * device after boot time, this will offline CPU0 and user may + * see different CPU0 state before and after accessing + * the snapshot device. But hopefully this is not a case when + * user debugging CPU0 hotplug. Even if users hit this case, + * they can easily online CPU0 back. + * + * To simplify this debug code, we only consider normal boot + * case. Otherwise we need to remember CPU0's state and restore + * to that state and resolve racy conditions etc. + */ + _debug_hotplug_cpu(0, 0); + break; +#endif default: break; } -- cgit v1.2.3 From 1022623842cb72ee4d0dbf02f6937f38c92c3f41 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 3 Sep 2012 20:54:48 +0200 Subject: x86-32: Fix invalid stack address while in softirq In 32 bit the stack address provided by kernel_stack_pointer() may point to an invalid range causing NULL pointer access or page faults while in NMI (see trace below). This happens if called in softirq context and if the stack is empty. The address at ®s->sp is then out of range. Fixing this by checking if regs and ®s->sp are in the same stack context. Otherwise return the previous stack pointer stored in struct thread_info. If that address is invalid too, return address of regs. BUG: unable to handle kernel NULL pointer dereference at 0000000a IP: [] print_context_stack+0x6e/0x8d *pde = 00000000 Oops: 0000 [#1] SMP Modules linked in: Pid: 4434, comm: perl Not tainted 3.6.0-rc3-oprofile-i386-standard-g4411a05 #4 Hewlett-Packard HP xw9400 Workstation/0A1Ch EIP: 0060:[] EFLAGS: 00010093 CPU: 0 EIP is at print_context_stack+0x6e/0x8d EAX: ffffe000 EBX: 0000000a ECX: f4435f94 EDX: 0000000a ESI: f4435f94 EDI: f4435f94 EBP: f5409ec0 ESP: f5409ea0 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 8005003b CR2: 0000000a CR3: 34ac9000 CR4: 000007d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: ffff0ff0 DR7: 00000400 Process perl (pid: 4434, ti=f5408000 task=f5637850 task.ti=f4434000) Stack: 000003e8 ffffe000 00001ffc f4e39b00 00000000 0000000a f4435f94 c155198c f5409ef0 c1003723 c155198c f5409f04 00000000 f5409edc 00000000 00000000 f5409ee8 f4435f94 f5409fc4 00000001 f5409f1c c12dce1c 00000000 c155198c Call Trace: [] dump_trace+0x7b/0xa1 [] x86_backtrace+0x40/0x88 [] ? oprofile_add_sample+0x56/0x84 [] oprofile_add_sample+0x75/0x84 [] op_amd_check_ctrs+0x46/0x260 [] profile_exceptions_notify+0x23/0x4c [] nmi_handle+0x31/0x4a [] ? ftrace_define_fields_irq_handler_entry+0x45/0x45 [] do_nmi+0xa0/0x2ff [] ? ftrace_define_fields_irq_handler_entry+0x45/0x45 [] nmi_stack_correct+0x28/0x2d [] ? ftrace_define_fields_irq_handler_entry+0x45/0x45 [] ? do_softirq+0x4b/0x7f [] irq_exit+0x35/0x5b [] smp_apic_timer_interrupt+0x6c/0x7a [] apic_timer_interrupt+0x2a/0x30 Code: 89 fe eb 08 31 c9 8b 45 0c ff 55 ec 83 c3 04 83 7d 10 00 74 0c 3b 5d 10 73 26 3b 5d e4 73 0c eb 1f 3b 5d f0 76 1a 3b 5d e8 73 15 <8b> 13 89 d0 89 55 e0 e8 ad 42 03 00 85 c0 8b 55 e0 75 a6 eb cc EIP: [] print_context_stack+0x6e/0x8d SS:ESP 0068:f5409ea0 CR2: 000000000000000a ---[ end trace 62afee3481b00012 ]--- Kernel panic - not syncing: Fatal exception in interrupt V2: * add comments to kernel_stack_pointer() * always return a valid stack address by falling back to the address of regs Reported-by: Yang Wei Cc: Signed-off-by: Robert Richter Link: http://lkml.kernel.org/r/20120912135059.GZ8285@erda.amd.com Signed-off-by: H. Peter Anvin Cc: Jun Zhang --- arch/x86/include/asm/ptrace.h | 15 ++++----------- arch/x86/kernel/ptrace.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 11 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index dcfde52979c3..19f16ebaf4fa 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs) } #endif -/* - * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode - * when it traps. The previous stack will be directly underneath the saved - * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. - * - * This is valid only for kernel mode traps. - */ -static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) -{ #ifdef CONFIG_X86_32 - return (unsigned long)(®s->sp); +extern unsigned long kernel_stack_pointer(struct pt_regs *regs); #else +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ return regs->sp; -#endif } +#endif #define GET_IP(regs) ((regs)->ip) #define GET_FP(regs) ((regs)->bp) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b00b33a18390..2484e331a64d 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -166,6 +166,34 @@ static inline bool invalid_selector(u16 value) #define FLAG_MASK FLAG_MASK_32 +/* + * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. + * + * Now, if the stack is empty, '®s->sp' is out of range. In this + * case we try to take the previous stack. To always return a non-null + * stack pointer we fall back to regs as stack if no previous stack + * exists. + * + * This is valid only for kernel mode traps. + */ +unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); + unsigned long sp = (unsigned long)®s->sp; + struct thread_info *tinfo; + + if (context == (sp & ~(THREAD_SIZE - 1))) + return sp; + + tinfo = (struct thread_info *)context; + if (tinfo->previous_esp) + return tinfo->previous_esp; + + return (unsigned long)regs; +} + static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); -- cgit v1.2.3 From cb57a2b4cff7edf2a4e32c0163200e9434807e0a Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 20 Nov 2012 22:21:02 -0800 Subject: x86-32: Export kernel_stack_pointer() for modules Modules, in particular oprofile (and possibly other similar tools) need kernel_stack_pointer(), so export it using EXPORT_SYMBOL_GPL(). Cc: Yang Wei Cc: Robert Richter Cc: Jun Zhang Cc: Link: http://lkml.kernel.org/r/20120912135059.GZ8285@erda.amd.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/ptrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2484e331a64d..5e0596b0632e 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -193,6 +194,7 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs) return (unsigned long)regs; } +EXPORT_SYMBOL_GPL(kernel_stack_pointer); static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { -- cgit v1.2.3 From 36c46ca4f322a7bf89aad5462a3a1f61713edce7 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Thu, 15 Nov 2012 13:41:50 -0500 Subject: x86, microcode, AMD: Add support for family 16h processors Add valid patch size for family 16h processors. [ hpa: promoting to urgent/stable since it is hw enabling and trivial ] Signed-off-by: Boris Ostrovsky Acked-by: Andreas Herrmann Link: http://lkml.kernel.org/r/1353004910-2204-1-git-send-email-boris.ostrovsky@amd.com Signed-off-by: H. Peter Anvin Cc: --- arch/x86/kernel/microcode_amd.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index b3e67ba55b77..efdec7cd8e01 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 +#define F16H_MPB_MAX_SIZE 3458 switch (c->x86) { case 0x14: @@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, case 0x15: max_size = F15H_MPB_MAX_SIZE; break; + case 0x16: + max_size = F16H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; -- cgit v1.2.3 From ee4eb87be2c3f69c2c4d9f1c1d98e363a7ad18ab Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 2 Nov 2012 11:18:39 +0000 Subject: x86-64: Fix ordering of CFI directives and recent ASM_CLAC additions While these got added in the right place everywhere else, entry_64.S is the odd one where they ended up before the initial CFI directive(s). In order to cover the full code ranges, the CFI directive must be first, though. Signed-off-by: Jan Beulich Link: http://lkml.kernel.org/r/5093BA1F02000078000A600E@nat28.tlf.novell.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/entry_64.S | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b51b2c7ee51f..1328fe49a3f1 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -995,8 +995,8 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC XCPT_FRAME + ASM_CLAC addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ /* 0(%rsp): old_rsp-ARGOFFSET */ @@ -1135,8 +1135,8 @@ END(common_interrupt) */ .macro apicinterrupt num sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC pushq_cfi $~(\num) .Lcommon_\sym: interrupt \do_sym @@ -1190,8 +1190,8 @@ apicinterrupt IRQ_WORK_VECTOR \ */ .macro zeroentry sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1208,8 +1208,8 @@ END(\sym) .macro paranoidzeroentry sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1227,8 +1227,8 @@ END(\sym) #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1247,8 +1247,8 @@ END(\sym) .macro errorentry sym do_sym ENTRY(\sym) - ASM_CLAC XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1266,8 +1266,8 @@ END(\sym) /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) - ASM_CLAC XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 -- cgit v1.2.3 From 29c574c0aba8dc0736e19eb9b24aad28cc5c9098 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 26 Nov 2012 14:49:36 -0800 Subject: x86, apic: Cleanup cfg->domain setup for legacy interrupts Issues that need to be handled: * Handle PIC interrupts on any CPU irrespective of the apic mode * In the apic lowest priority logical flat delivery mode, be prepared to handle the interrupt on any CPU irrespective of what the IO-APIC RTE says. * Because of above, when the IO-APIC starts handling the legacy PIC interrupt, use the same vector that is being used by the PIC while programming the corresponding IO-APIC RTE. Start with all the cpu's in the legacy PIC interrupts cfg->domain. By the time IO-APIC starts taking over the PIC interrupts, apic driver model is finalized. So depend on the assign_irq_vector() to update the cfg->domain and retain the same vector that was used by PIC before. For the logical apic flat mode, cfg->domain is updated (during the first call to assign_irq_vector()) to contain all the possible online cpu's (0xff). Vector used for the legacy PIC interrupt doesn't change when the IO-APIC starts handling the interrupt. Any interrupt migration after that doesn't change the cfg->domain or the vector used. For other apic modes like physical mode, cfg->domain is updated (during the first call to assign_irq_vector()) to the boot cpu (cpu-0), with the same vector that is being used by the PIC. When that interrupt is migrated to a different cpu, cfg->domin and the vector assigned will change accordingly. Tested-by: Borislav Petkov Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1353970176.21070.51.camel@sbsiddha-desk.sc.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/io_apic.c | 26 ++++++-------------------- 1 file changed, 6 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c265593ec2cd..0c1f36650568 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -234,11 +234,11 @@ int __init arch_early_irq_init(void) zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); /* * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0. + * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. */ if (i < legacy_pic->nr_legacy_irqs) { cfg[i].vector = IRQ0_VECTOR + i; - cpumask_set_cpu(0, cfg[i].domain); + cpumask_setall(cfg[i].domain); } } @@ -1141,7 +1141,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * allocation for the members that are not used anymore. */ cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = 1; + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); cpumask_and(cfg->domain, cfg->domain, tmp_mask); break; } @@ -1172,8 +1173,9 @@ next: current_vector = vector; current_offset = offset; if (cfg->vector) { - cfg->move_in_progress = 1; cpumask_copy(cfg->old_domain, cfg->domain); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); } for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; @@ -1241,12 +1243,6 @@ void __setup_vector_irq(int cpu) cfg = irq_get_chip_data(irq); if (!cfg) continue; - /* - * If it is a legacy IRQ handled by the legacy PIC, this cpu - * will be part of the irq_cfg's domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq)) - cpumask_set_cpu(cpu, cfg->domain); if (!cpumask_test_cpu(cpu, cfg->domain)) continue; @@ -1356,16 +1352,6 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC - * can handle this irq and the apic driver is finialized at this point, - * update the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && - cpumask_equal(cfg->domain, cpumask_of(0))) - apic->vector_allocation_domain(0, cfg->domain, - apic->target_cpus()); - if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; -- cgit v1.2.3 From 6662c34fa9c60a48aaa5879cb229cd9a84de9c22 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 27 Nov 2012 08:54:36 -0800 Subject: x86-32: Unbreak booting on some 486 clones There appear to have been some 486 clones, including the "enhanced" version of Am486, which have CPUID but not CR4. These 486 clones had only the FPU flag, if any, unlike the Intel 486s with CPUID, which also had VME and therefore needed CR4. Therefore, look at the basic CPUID flags and require at least one bit other than bit 0 before we modify CR4. Thanks to Christian Ludloff of sandpile.org for confirming this as a problem. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 957a47aec64e..4dac2f68ed4a 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -292,8 +292,8 @@ default_entry: * be using the global pages. * * NOTE! If we are on a 486 we may have no cr4 at all! - * Specifically, cr4 exists if and only if CPUID exists, - * which in turn exists if and only if EFLAGS.ID exists. + * Specifically, cr4 exists if and only if CPUID exists + * and has flags other than the FPU flag set. */ movl $X86_EFLAGS_ID,%ecx pushl %ecx @@ -308,6 +308,11 @@ default_entry: testl %ecx,%eax jz 6f # No ID flag = no CPUID = no CR4 + movl $1,%eax + cpuid + andl $~1,%edx # Ignore CPUID.FPU + jz 6f # No flags or only CPUID.FPU = no CR4 + movl pa(mmu_cr4_features),%eax movl %eax,%cr4 -- cgit v1.2.3 From 7069ed67635b8d574541af426d752cd7fbd465a6 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:48 -0200 Subject: x86: kvmclock: allocate pvclock shared memory area We want to expose the pvclock shared memory areas, which the hypervisor periodically updates, to userspace. For a linear mapping from userspace, it is necessary that entire page sized regions are used for array of pvclock structures. There is no such guarantee with per cpu areas, therefore move to memblock_alloc based allocation. Acked-by: Glauber Costa Signed-off-by: Marcelo Tosatti --- arch/x86/kernel/kvmclock.c | 58 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 47 insertions(+), 11 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index f1b42b3a186c..c7d75678886e 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -39,7 +40,11 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +struct pvclock_aligned_vcpu_time_info { + struct pvclock_vcpu_time_info clock; +} __attribute__((__aligned__(SMP_CACHE_BYTES))); + +static struct pvclock_aligned_vcpu_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; /* @@ -52,15 +57,20 @@ static unsigned long kvm_get_wallclock(void) struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; int low, high; + int cpu; low = (int)__pa_symbol(&wall_clock); high = ((u64)__pa_symbol(&wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); - vcpu_time = &get_cpu_var(hv_clock); + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].clock; pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); - put_cpu_var(hv_clock); + + preempt_enable(); return ts.tv_sec; } @@ -74,9 +84,11 @@ static cycle_t kvm_clock_read(void) { struct pvclock_vcpu_time_info *src; cycle_t ret; + int cpu; preempt_disable_notrace(); - src = &__get_cpu_var(hv_clock); + cpu = smp_processor_id(); + src = &hv_clock[cpu].clock; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -99,8 +111,15 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) static unsigned long kvm_get_tsc_khz(void) { struct pvclock_vcpu_time_info *src; - src = &per_cpu(hv_clock, 0); - return pvclock_tsc_khz(src); + int cpu; + unsigned long tsc_khz; + + preempt_disable(); + cpu = smp_processor_id(); + src = &hv_clock[cpu].clock; + tsc_khz = pvclock_tsc_khz(src); + preempt_enable(); + return tsc_khz; } static void kvm_get_preset_lpj(void) @@ -119,10 +138,14 @@ bool kvm_check_and_clear_guest_paused(void) { bool ret = false; struct pvclock_vcpu_time_info *src; + int cpu = smp_processor_id(); + + if (!hv_clock) + return ret; - src = &__get_cpu_var(hv_clock); + src = &hv_clock[cpu].clock; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { - __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED); + src->flags &= ~PVCLOCK_GUEST_STOPPED; ret = true; } @@ -141,9 +164,10 @@ int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high, ret; + struct pvclock_vcpu_time_info *src = &hv_clock[cpu].clock; - low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; - high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); + low = (int)__pa(src) | 1; + high = ((u64)__pa(src) >> 32); ret = native_write_msr_safe(msr_kvm_system_time, low, high); printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", cpu, high, low, txt); @@ -197,6 +221,8 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + unsigned long mem; + if (!kvm_para_available()) return; @@ -209,8 +235,18 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - if (kvm_register_clock("boot clock")) + mem = memblock_alloc(sizeof(struct pvclock_aligned_vcpu_time_info) * NR_CPUS, + PAGE_SIZE); + if (!mem) + return; + hv_clock = __va(mem); + + if (kvm_register_clock("boot clock")) { + hv_clock = NULL; + memblock_free(mem, + sizeof(struct pvclock_aligned_vcpu_time_info)*NR_CPUS); return; + } pv_time_ops.sched_clock = kvm_clock_read; x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; -- cgit v1.2.3 From b01578de45614c085be319229a52774b61ffe6fb Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:49 -0200 Subject: x86: pvclock: make sure rdtsc doesnt speculate out of region Originally from Jeremy Fitzhardinge. pvclock_get_time_values, which contains the memory barriers will be removed by next patch. Signed-off-by: Marcelo Tosatti --- arch/x86/kernel/pvclock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 42eb3300dfc6..12e47e210491 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -97,10 +97,10 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = pvclock_get_time_values(&shadow, src); - barrier(); + rdtsc_barrier(); offset = pvclock_get_nsec_offset(&shadow); ret = shadow.system_timestamp + offset; - barrier(); + rdtsc_barrier(); } while (version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && -- cgit v1.2.3 From 42b5637d6989f75a7a0e8ea8633583564ff443ff Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:50 -0200 Subject: x86: pvclock: remove pvclock_shadow_time Originally from Jeremy Fitzhardinge. We can copy the information directly from "struct pvclock_vcpu_time_info", remove pvclock_shadow_time. Reviewed-by: Glauber Costa Signed-off-by: Marcelo Tosatti --- arch/x86/kernel/pvclock.c | 57 +++++++++-------------------------------------- 1 file changed, 11 insertions(+), 46 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 12e47e210491..d59e60661794 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -19,21 +19,6 @@ #include #include -/* - * These are perodically updated - * xen: magic shared_info page - * kvm: gpa registered via msr - * and then copied here. - */ -struct pvclock_shadow_time { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; - u8 flags; -}; - static u8 valid_flags __read_mostly = 0; void pvclock_set_flags(u8 flags) @@ -41,32 +26,11 @@ void pvclock_set_flags(u8 flags) valid_flags = flags; } -static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) -{ - u64 delta = native_read_tsc() - shadow->tsc_timestamp; - return pvclock_scale_delta(delta, shadow->tsc_to_nsec_mul, - shadow->tsc_shift); -} - -/* - * Reads a consistent set of time-base values from hypervisor, - * into a shadow data area. - */ -static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, - struct pvclock_vcpu_time_info *src) +static u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) { - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - dst->flags = src->flags; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) || (dst->version != src->version)); - - return dst->version; + u64 delta = native_read_tsc() - src->tsc_timestamp; + return pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); } unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) @@ -90,21 +54,22 @@ void pvclock_resume(void) cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { - struct pvclock_shadow_time shadow; unsigned version; cycle_t ret, offset; u64 last; + u8 flags; do { - version = pvclock_get_time_values(&shadow, src); + version = src->version; rdtsc_barrier(); - offset = pvclock_get_nsec_offset(&shadow); - ret = shadow.system_timestamp + offset; + offset = pvclock_get_nsec_offset(src); + ret = src->system_time + offset; + flags = src->flags; rdtsc_barrier(); - } while (version != src->version); + } while ((src->version & 1) || version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && - (shadow.flags & PVCLOCK_TSC_STABLE_BIT)) + (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; /* -- cgit v1.2.3 From dce2db0a35197e2f4421245079f19ab753e97348 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:51 -0200 Subject: x86: pvclock: create helper for pvclock data retrieval Originally from Jeremy Fitzhardinge. So code can be reused. Acked-by: Glauber Costa Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/pvclock.h | 28 ++++++++++++++++++++++++++++ arch/x86/kernel/pvclock.c | 16 ++-------------- 2 files changed, 30 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index c59cc97fe6c1..47e25d464104 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -56,4 +56,32 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) return product; } +static __always_inline +u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) +{ + u64 delta = __native_read_tsc() - src->tsc_timestamp; + return pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); +} + +static __always_inline +unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, + cycle_t *cycles, u8 *flags) +{ + unsigned version; + cycle_t ret, offset; + u8 ret_flags; + + version = src->version; + rdtsc_barrier(); + offset = pvclock_get_nsec_offset(src); + ret = src->system_time + offset; + ret_flags = src->flags; + rdtsc_barrier(); + + *cycles = ret; + *flags = ret_flags; + return version; +} + #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index d59e60661794..a7d90910c61a 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -26,13 +26,6 @@ void pvclock_set_flags(u8 flags) valid_flags = flags; } -static u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = native_read_tsc() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) { u64 pv_tsc_khz = 1000000ULL << 32; @@ -55,17 +48,12 @@ void pvclock_resume(void) cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret, offset; + cycle_t ret; u64 last; u8 flags; do { - version = src->version; - rdtsc_barrier(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - flags = src->flags; - rdtsc_barrier(); + version = __pvclock_read_cycles(src, &ret, &flags); } while ((src->version & 1) || version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && -- cgit v1.2.3 From 2697902be89d7f38e9736dfe946cd0e5d4f47b80 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:52 -0200 Subject: x86: pvclock: introduce helper to read flags Acked-by: Glauber Costa Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/pvclock.h | 1 + arch/x86/kernel/pvclock.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 47e25d464104..ea27a8dd189c 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -6,6 +6,7 @@ /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); void pvclock_set_flags(u8 flags); unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); void pvclock_read_wallclock(struct pvclock_wall_clock *wall, diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index a7d90910c61a..c8fb043a8695 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -45,6 +45,19 @@ void pvclock_resume(void) atomic64_set(&last_value, 0); } +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) +{ + unsigned version; + cycle_t ret; + u8 flags; + + do { + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); + + return flags & valid_flags; +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { unsigned version; -- cgit v1.2.3 From 71056ae22d43f58d7e0f793af18ace2eaf5b74eb Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:55 -0200 Subject: x86: pvclock: generic pvclock vsyscall initialization Originally from Jeremy Fitzhardinge. Introduce generic, non hypervisor specific, pvclock initialization routines. Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/clocksource.h | 1 + arch/x86/include/asm/fixmap.h | 5 +++ arch/x86/include/asm/pvclock.h | 12 +++++++ arch/x86/kernel/pvclock.c | 73 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 91 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index 0bdbbb3b9ce7..16a57f4ed64d 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -8,6 +8,7 @@ #define VCLOCK_NONE 0 /* No vDSO clock available. */ #define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ #define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ +#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 4da3c0c4c974..a09c28571064 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef CONFIG_X86_32 #include #include @@ -80,6 +81,10 @@ enum fixed_addresses { + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, VVAR_PAGE, VSYSCALL_HPET, +#endif +#ifdef CONFIG_PARAVIRT_CLOCK + PVCLOCK_FIXMAP_BEGIN, + PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 63f91679af73..109a9dd5d454 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -91,4 +91,16 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, return version; } +struct pvclock_vsyscall_time_info { + struct pvclock_vcpu_time_info pvti; + u32 migrate_count; +} __attribute__((__aligned__(SMP_CACHE_BYTES))); + +#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) +#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size); +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); + #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index c8fb043a8695..85c39590c1a4 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -17,6 +17,11 @@ #include #include +#include +#include +#include +#include +#include #include static u8 valid_flags __read_mostly = 0; @@ -122,3 +127,71 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + +#ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + +/* + * Initialize the generic pvclock vsyscall state. This will allocate + * a/some page(s) for the per-vcpu pvclock information, set up a + * fixmap mapping for the page(s) + */ + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size) +{ + int idx; + + WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + + pvclock_vdso_info = i; + + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { + __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, + __pa_symbol(i) + (idx*PAGE_SIZE), + PAGE_KERNEL_VVAR); + } + + + register_task_migration_notifier(&pvclock_migrate); + + return 0; +} +#endif -- cgit v1.2.3 From 3dc4f7cfb7441e5e0fed3a02fc81cdaabd28300a Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Nov 2012 23:28:56 -0200 Subject: x86: kvm guest: pvclock vsyscall support Hook into generic pvclock vsyscall code, with the aim to allow userspace to have visibility into pvclock data. Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_guest.h | 6 +++++ arch/x86/kernel/kvm.c | 13 ++++++++++ arch/x86/kernel/kvmclock.c | 54 +++++++++++++++++++++++++++++++--------- 3 files changed, 61 insertions(+), 12 deletions(-) create mode 100644 arch/x86/include/asm/kvm_guest.h (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h new file mode 100644 index 000000000000..a92b1763c419 --- /dev/null +++ b/arch/x86/include/asm/kvm_guest.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_KVM_GUEST_H +#define _ASM_X86_KVM_GUEST_H + +int kvm_setup_vsyscall_timeinfo(void); + +#endif /* _ASM_X86_KVM_GUEST_H */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4180a874c764..a91c6b482b48 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -42,6 +42,7 @@ #include #include #include +#include static int kvmapf = 1; @@ -62,6 +63,15 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static int kvmclock_vsyscall = 1; +static int parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} + +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; @@ -471,6 +481,9 @@ void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvmclock_vsyscall) + kvm_setup_vsyscall_timeinfo(); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index c7d75678886e..220a360010f8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -40,11 +40,7 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -struct pvclock_aligned_vcpu_time_info { - struct pvclock_vcpu_time_info clock; -} __attribute__((__aligned__(SMP_CACHE_BYTES))); - -static struct pvclock_aligned_vcpu_time_info *hv_clock; +static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; /* @@ -67,7 +63,7 @@ static unsigned long kvm_get_wallclock(void) preempt_disable(); cpu = smp_processor_id(); - vcpu_time = &hv_clock[cpu].clock; + vcpu_time = &hv_clock[cpu].pvti; pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); preempt_enable(); @@ -88,7 +84,7 @@ static cycle_t kvm_clock_read(void) preempt_disable_notrace(); cpu = smp_processor_id(); - src = &hv_clock[cpu].clock; + src = &hv_clock[cpu].pvti; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -116,7 +112,7 @@ static unsigned long kvm_get_tsc_khz(void) preempt_disable(); cpu = smp_processor_id(); - src = &hv_clock[cpu].clock; + src = &hv_clock[cpu].pvti; tsc_khz = pvclock_tsc_khz(src); preempt_enable(); return tsc_khz; @@ -143,7 +139,7 @@ bool kvm_check_and_clear_guest_paused(void) if (!hv_clock) return ret; - src = &hv_clock[cpu].clock; + src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { src->flags &= ~PVCLOCK_GUEST_STOPPED; ret = true; @@ -164,7 +160,7 @@ int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high, ret; - struct pvclock_vcpu_time_info *src = &hv_clock[cpu].clock; + struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti; low = (int)__pa(src) | 1; high = ((u64)__pa(src) >> 32); @@ -235,7 +231,7 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - mem = memblock_alloc(sizeof(struct pvclock_aligned_vcpu_time_info) * NR_CPUS, + mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS, PAGE_SIZE); if (!mem) return; @@ -244,7 +240,7 @@ void __init kvmclock_init(void) if (kvm_register_clock("boot clock")) { hv_clock = NULL; memblock_free(mem, - sizeof(struct pvclock_aligned_vcpu_time_info)*NR_CPUS); + sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); return; } pv_time_ops.sched_clock = kvm_clock_read; @@ -269,3 +265,37 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } + +int __init kvm_setup_vsyscall_timeinfo(void) +{ +#ifdef CONFIG_X86_64 + int cpu; + int ret; + u8 flags; + struct pvclock_vcpu_time_info *vcpu_time; + unsigned int size; + + size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS; + + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { + preempt_enable(); + return 1; + } + + if ((ret = pvclock_init_vsyscall(hv_clock, size))) { + preempt_enable(); + return ret; + } + + preempt_enable(); + + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; +#endif + return 0; +} -- cgit v1.2.3 From 859f8450d8a334a7f7cb994e4676cf918deff832 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 28 Nov 2012 15:19:08 +0200 Subject: KVM: use is_idle_task() instead of idle_cpu() to decide when to halt in async_pf As Frederic pointed idle_cpu() may return false even if async fault happened in the idle task if wake up is pending. In this case the code will try to put idle task to sleep. Fix this by using is_idle_task() to check for idle task. Reported-by: Frederic Weisbecker Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- arch/x86/kernel/kvm.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a91c6b482b48..08b973f64032 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -120,11 +120,6 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); - int cpu, idle; - - cpu = get_cpu(); - idle = idle_cpu(cpu); - put_cpu(); spin_lock(&b->lock); e = _find_apf_task(b, token); @@ -138,7 +133,7 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = idle || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1; init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); -- cgit v1.2.3 From 1d4b4b2994b5fc208963c0b795291f8c1f18becf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Oct 2012 22:34:11 -0400 Subject: x86, um: switch to generic fork/vfork/clone Signed-off-by: Al Viro --- arch/um/kernel/syscall.c | 19 ------------------- arch/x86/Kconfig | 1 + arch/x86/ia32/ia32entry.S | 7 ++++++- arch/x86/ia32/sys_ia32.c | 11 ----------- arch/x86/include/asm/sys_ia32.h | 2 -- arch/x86/include/asm/syscalls.h | 13 +++++++++---- arch/x86/include/asm/unistd.h | 3 +++ arch/x86/kernel/entry_32.S | 18 ------------------ arch/x86/kernel/entry_64.S | 22 +++++++++++++++++++--- arch/x86/kernel/process.c | 30 ------------------------------ arch/x86/kernel/process_32.c | 11 ++++++----- arch/x86/kernel/process_64.c | 7 ++++--- arch/x86/syscalls/syscall_32.tbl | 6 +++--- arch/x86/um/Kconfig | 1 + arch/x86/um/sys_call_table_32.c | 3 --- arch/x86/um/syscalls_32.c | 15 --------------- 16 files changed, 52 insertions(+), 117 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 3a875226c8ef..c1d0ae069b53 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -14,25 +14,6 @@ #include #include -long sys_fork(void) -{ - return do_fork(SIGCHLD, 0, - ¤t->thread.regs, 0, NULL, NULL); -} - -long sys_vfork(void) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, - ¤t->thread.regs, 0, NULL, NULL); -} - -long sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid) -{ - return do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); -} - long old_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long offset) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 46c3bff3ced2..0df6e7d84539 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -112,6 +112,7 @@ config X86 select GENERIC_KERNEL_EXECVE select MODULES_USE_ELF_REL if X86_32 select MODULES_USE_ELF_RELA if X86_64 + select CLONE_BACKWARDS if X86_32 config INSTRUCTION_DECODER def_bool y diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 076745fc8045..32e6f05ddaaa 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -467,10 +467,15 @@ GLOBAL(\label) PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx PTREGSCALL stub32_execve, compat_sys_execve, %rcx PTREGSCALL stub32_fork, sys_fork, %rdi - PTREGSCALL stub32_clone, sys32_clone, %rdx PTREGSCALL stub32_vfork, sys_vfork, %rdi PTREGSCALL stub32_iopl, sys_iopl, %rsi + ALIGN +GLOBAL(stub32_clone) + leaq sys_clone(%rip),%rax + mov %r8, %rcx + jmp ia32_ptregs_common + ALIGN ia32_ptregs_common: popq %r11 diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 86d68d1c8806..d0b689ba7be2 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -385,17 +385,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd, return ret; } -asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp, - struct pt_regs *regs) -{ - void __user *parent_tid = (void __user *)regs->dx; - void __user *child_tid = (void __user *)regs->di; - - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - /* * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index a9a8cf3da49d..c76fae4d90be 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -54,8 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); - long sys32_lseek(unsigned int, int, unsigned int); long sys32_kill(int, int); long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 9e5aef3a2598..f7252d11416b 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -21,10 +21,15 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); long sys_iopl(unsigned int, struct pt_regs *); /* kernel/process.c */ -int sys_fork(struct pt_regs *); -int sys_vfork(struct pt_regs *); -long sys_clone(unsigned long, unsigned long, void __user *, - void __user *, struct pt_regs *); +asmlinkage long sys_fork(void); +asmlinkage long sys_vfork(void); +#ifdef CONFIG_CLONE_BACKWARDS +asmlinkage long sys_clone(unsigned long, unsigned long, void __user *, int, + void __user *); +#else +asmlinkage long sys_clone(unsigned long, unsigned long, void __user *, + void __user *, int); +#endif /* kernel/ldt.c */ asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 16f3fc6ebf2e..0e7dea7d3669 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -51,6 +51,9 @@ # define __ARCH_WANT_SYS_UTIME # define __ARCH_WANT_SYS_WAITPID # define __ARCH_WANT_SYS_EXECVE +# define __ARCH_WANT_SYS_FORK +# define __ARCH_WANT_SYS_VFORK +# define __ARCH_WANT_SYS_CLONE /* * "Conditional" syscalls diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 88b725aa1d52..c763116c5359 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -739,30 +739,12 @@ ENTRY(ptregs_##name) ; \ ENDPROC(ptregs_##name) PTREGSCALL1(iopl) -PTREGSCALL0(fork) -PTREGSCALL0(vfork) PTREGSCALL2(sigaltstack) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) PTREGSCALL1(vm86old) -/* Clone is an oddball. The 4th arg is in %edi */ -ENTRY(ptregs_clone) - CFI_STARTPROC - leal 4(%esp),%eax - pushl_cfi %eax - pushl_cfi PT_EDI(%eax) - movl PT_EDX(%eax),%ecx - movl PT_ECX(%eax),%edx - movl PT_EBX(%eax),%eax - call sys_clone - addl $8,%esp - CFI_ADJUST_CFA_OFFSET -8 - ret - CFI_ENDPROC -ENDPROC(ptregs_clone) - .macro FIXUP_ESPFIX_STACK /* * Switch back for ESPFIX stack to the normal zerobased stack diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1328fe49a3f1..2363e820ed68 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -845,9 +845,25 @@ ENTRY(\label) END(\label) .endm - PTREGSCALL stub_clone, sys_clone, %r8 - PTREGSCALL stub_fork, sys_fork, %rdi - PTREGSCALL stub_vfork, sys_vfork, %rdi + .macro FORK_LIKE func +ENTRY(stub_\func) + CFI_STARTPROC + popq %r11 /* save return address */ + PARTIAL_FRAME 0 + SAVE_REST + pushq %r11 /* put it back on stack */ + FIXUP_TOP_OF_STACK %r11, 8 + DEFAULT_FRAME 0 8 /* offset 8: return address */ + call sys_\func + RESTORE_TOP_OF_STACK %r11, 8 + ret $REST_SKIP /* pop extended registers */ + CFI_ENDPROC +END(stub_\func) + .endm + + FORK_LIKE clone + FORK_LIKE fork + FORK_LIKE vfork PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx PTREGSCALL stub_iopl, sys_iopl, %rsi diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b644e1c765dc..fe9459593257 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -262,36 +262,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, propagate_user_return_notify(prev_p, next_p); } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, - NULL, NULL); -} - -long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - /* * Idle related variables and functions */ diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 44e0bff38e72..16efa974532b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -129,7 +129,7 @@ void release_thread(struct task_struct *dead_task) int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + struct task_struct *p, struct pt_regs *unused) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -138,7 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); - if (unlikely(!regs)) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); p->thread.ip = (unsigned long) ret_from_kernel_thread; @@ -156,12 +156,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; } - *childregs = *regs; + *childregs = *current_pt_regs(); childregs->ax = 0; - childregs->sp = sp; + if (sp) + childregs->sp = sp; p->thread.ip = (unsigned long) ret_from_fork; - task_user_gs(p) = get_user_gs(regs); + task_user_gs(p) = get_user_gs(current_pt_regs()); p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 16c6365e2b86..74aac76c6e34 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -169,7 +169,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, savesegment(ds, p->thread.ds); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(!regs)) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->sp = (unsigned long)childregs; @@ -181,10 +181,11 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; return 0; } - *childregs = *regs; + *childregs = *current_pt_regs(); childregs->ax = 0; - childregs->sp = sp; + if (sp) + childregs->sp = sp; err = -ENOMEM; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index a47103fbc692..ee3c220ee500 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -8,7 +8,7 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork ptregs_fork stub32_fork +2 i386 fork sys_fork stub32_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc sys32_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn ptregs_sigreturn stub32_sigreturn -120 i386 clone ptregs_clone stub32_clone +120 i386 clone sys_clone stub32_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt @@ -196,7 +196,7 @@ 187 i386 sendfile sys_sendfile sys32_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork ptregs_vfork stub32_vfork +190 i386 vfork sys_vfork stub32_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff 193 i386 truncate64 sys_truncate64 sys32_truncate64 diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 07611759ce35..8f51c39750d1 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -25,6 +25,7 @@ config X86_32 select HAVE_AOUT select ARCH_WANT_IPC_PARSE_VERSION select MODULES_USE_ELF_REL + select CLONE_BACKWARDS config X86_64 def_bool 64BIT diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 232e60504b3a..812e98c098e4 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -24,13 +24,10 @@ #define old_mmap sys_old_mmap -#define ptregs_fork sys_fork #define ptregs_iopl sys_iopl #define ptregs_vm86old sys_vm86old -#define ptregs_clone i386_clone #define ptregs_vm86 sys_vm86 #define ptregs_sigaltstack sys_sigaltstack -#define ptregs_vfork sys_vfork #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; #include diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c index db444c7218fe..e8bcea99acdb 100644 --- a/arch/x86/um/syscalls_32.c +++ b/arch/x86/um/syscalls_32.c @@ -6,21 +6,6 @@ #include #include -/* - * The prototype on i386 is: - * - * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls - * - * and the "newtls" arg. on i386 is read by copy_thread directly from the - * register saved on the stack. - */ -long i386_clone(unsigned long clone_flags, unsigned long newsp, - int __user *parent_tid, void *newtls, int __user *child_tid) -{ - return sys_clone(clone_flags, newsp, parent_tid, child_tid); -} - - long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { -- cgit v1.2.3 From afa86fc426ff7e7f5477f15da9c405d08d5cf790 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Oct 2012 22:51:14 -0400 Subject: flagday: don't pass regs to copy_thread() Signed-off-by: Al Viro --- arch/alpha/kernel/process.c | 2 +- arch/arm/kernel/process.c | 2 +- arch/arm64/kernel/process.c | 3 +-- arch/avr32/kernel/process.c | 2 +- arch/blackfin/kernel/process.c | 6 +++--- arch/c6x/kernel/process.c | 2 +- arch/cris/arch-v10/kernel/process.c | 3 +-- arch/cris/arch-v32/kernel/process.c | 3 +-- arch/frv/kernel/process.c | 2 +- arch/h8300/kernel/process.c | 2 +- arch/hexagon/kernel/process.c | 3 +-- arch/ia64/kernel/process.c | 3 ++- arch/m32r/kernel/process.c | 2 +- arch/m68k/kernel/process.c | 3 +-- arch/microblaze/kernel/process.c | 3 +-- arch/mips/kernel/process.c | 4 ++-- arch/mn10300/kernel/process.c | 2 +- arch/openrisc/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 5 ++--- arch/powerpc/kernel/process.c | 4 ++-- arch/s390/kernel/process.c | 3 +-- arch/score/kernel/process.c | 4 ++-- arch/sh/kernel/process_32.c | 3 +-- arch/sh/kernel/process_64.c | 5 ++--- arch/sparc/kernel/process_32.c | 5 ++--- arch/sparc/kernel/process_64.c | 4 ++-- arch/tile/kernel/process.c | 5 ++--- arch/um/kernel/process.c | 3 +-- arch/unicore32/kernel/process.c | 2 +- arch/x86/kernel/process_32.c | 3 +-- arch/x86/kernel/process_64.c | 3 +-- arch/xtensa/kernel/process.c | 3 +-- include/linux/sched.h | 2 +- kernel/fork.c | 2 +- 34 files changed, 45 insertions(+), 60 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index e9705bcc96f9..b5d0d0923699 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -241,7 +241,7 @@ release_thread(struct task_struct *dead_task) int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, struct pt_regs *wontuse) + struct task_struct *p) { extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 4ab80bbb6d95..9800338c5d1b 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -376,7 +376,7 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p, struct pt_regs *unused) + unsigned long stk_sz, struct task_struct *p) { struct thread_info *thread = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 5a1335caf6f1..cb0956bc96ed 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -234,8 +234,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) asmlinkage void ret_from_fork(void) asm("ret_from_fork"); int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p, - struct pt_regs *unused) + unsigned long stk_sz, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); unsigned long tls = p->thread.tp_value; diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 03d7aa4a4bc9..fd78f58ea79a 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -299,7 +299,7 @@ asmlinkage void syscall_return(void); int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index e5ae8fcab438..582276efaaa4 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -141,14 +141,14 @@ asmlinkage int bfin_clone(unsigned long clone_flags, unsigned long newsp) int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, - struct task_struct *p, struct pt_regs *regs) + struct task_struct *p) { struct pt_regs *childregs; unsigned long *v; childregs = (struct pt_regs *) (task_stack_page(p) + THREAD_SIZE) - 1; v = ((unsigned long *)childregs) - 2; - if (unlikely(!regs)) { + if (unlikely(p->flags & PF_KTHREAD)) { memset(childregs, 0, sizeof(struct pt_regs)); v[0] = usp; v[1] = topstk; @@ -157,7 +157,7 @@ copy_thread(unsigned long clone_flags, __asm__ __volatile__("%0 = syscfg;":"=da"(childregs->syscfg):); p->thread.usp = 0; } else { - *childregs = *regs; + *childregs = *current_pt_regs(); childregs->r0 = 0; p->thread.usp = usp ? : rdusp(); v[0] = v[1] = 0; diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c index a3f91895e8b4..6434df476f77 100644 --- a/arch/c6x/kernel/process.c +++ b/arch/c6x/kernel/process.c @@ -139,7 +139,7 @@ void start_thread(struct pt_regs *regs, unsigned int pc, unsigned long usp) */ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long ustk_size, - struct task_struct *p, struct pt_regs *unused) + struct task_struct *p) { struct pt_regs *childregs; diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index 520547c8b196..b1018750cffb 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -94,8 +94,7 @@ asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); struct switch_stack *swstack = ((struct switch_stack *)childregs) - 1; diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index 331e70252df0..2b23ef0e4452 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -109,8 +109,7 @@ extern asmlinkage void ret_from_kernel_thread(void); int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); struct switch_stack *swstack = ((struct switch_stack *) childregs) - 1; diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 0039bf77b192..23916b2a12a2 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -144,7 +144,7 @@ inline unsigned long user_stack(const struct pt_regs *regs) */ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + struct task_struct *p) { struct pt_regs *childregs; diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index b0fb4054aee5..b609f63f1590 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -129,7 +129,7 @@ void flush_thread(void) int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, - struct task_struct * p, struct pt_regs *unused) + struct task_struct * p) { struct pt_regs * childregs; diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 36dce17ed25c..06ae9ffcabd5 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -87,8 +87,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk) * Copy architecture-specific thread state */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p, - struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct thread_info *ti = task_thread_info(p); struct hexagon_switch_stack *ss; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 25543a295ad9..31360cbbd5f8 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -393,12 +393,13 @@ ia64_load_extra (struct task_struct *task) int copy_thread(unsigned long clone_flags, unsigned long user_stack_base, unsigned long user_stack_size, - struct task_struct *p, struct pt_regs *regs) + struct task_struct *p) { extern char ia64_ret_from_clone; struct switch_stack *child_stack, *stack; unsigned long rbs, child_rbs, rbs_size; struct pt_regs *child_ptregs; + struct pt_regs *regs = current_pt_regs(); int retval = 0; child_ptregs = (struct pt_regs *) ((unsigned long) p + IA64_STK_OFFSET) - 1; diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index c37e9a9a8f27..765d0f57c787 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -192,7 +192,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) } int copy_thread(unsigned long clone_flags, unsigned long spu, - unsigned long arg, struct task_struct *tsk, struct pt_regs *unused) + unsigned long arg, struct task_struct *tsk) { struct pt_regs *childregs = task_pt_regs(tsk); extern void ret_from_fork(void); diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index aa9b11000273..9a3df4df73cc 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -154,8 +154,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs) } int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct * p, struct pt_regs * unused) + unsigned long arg, struct task_struct *p) { struct fork_frame { struct switch_stack sw; diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a5fed8db7263..40823fd1db0b 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -120,8 +120,7 @@ void flush_thread(void) } int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); struct thread_info *ti = task_thread_info(p); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index d13720ac656f..38097652d62d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -114,10 +114,10 @@ void flush_thread(void) } int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct thread_info *ti = task_thread_info(p); - struct pt_regs *childregs; + struct pt_regs *childregs, *regs = current_pt_regs(); unsigned long childksp; p->set_child_tid = p->clear_child_tid = NULL; diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 5e0ef396458d..eb09f5a552ff 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -206,7 +206,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) */ int copy_thread(unsigned long clone_flags, unsigned long c_usp, unsigned long ustk_size, - struct task_struct *p, struct pt_regs *unused) + struct task_struct *p) { struct thread_info *ti = task_thread_info(p); struct pt_regs *c_regs; diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 6b853668369b..00c233bf0d06 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -142,7 +142,7 @@ extern asmlinkage void ret_from_fork(void); int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct pt_regs *userregs; struct pt_regs *kregs; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 9753ecf49a06..d13507246c5d 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -204,10 +204,9 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r) int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { - struct pt_regs * cregs = &(p->thread.regs); + struct pt_regs *cregs = &(p->thread.regs); void *stack = task_stack_page(p); /* We have to use void * instead of a function pointer, because diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a31437567631..81430674e71c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -733,8 +733,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p, - struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); @@ -759,6 +758,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; } else { + struct pt_regs *regs = current_pt_regs(); CHECK_FULL_REGS(regs); *childregs = *regs; if (usp) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index e37677796a09..536d64579d9a 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -117,8 +117,7 @@ void release_thread(struct task_struct *dead_task) } int copy_thread(unsigned long clone_flags, unsigned long new_stackp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct thread_info *ti; struct fake_frame diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index f96379a5aee0..79568466b578 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -87,11 +87,11 @@ void flush_thread(void) {} * set up the kernel stack and exception frames for a new process */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); + struct pt_regs *regs = current_pt_regs(); p->thread.reg0 = (unsigned long) childregs; if (unlikely(p->flags & PF_KTHREAD)) { diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 1786d16b6c64..73eb66fc6253 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -128,8 +128,7 @@ asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs; diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index d5c86a8a3849..e611c85144b1 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -371,10 +371,9 @@ asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { - struct pt_regs *childregs; + struct pt_regs *childregs, *regs = current_pt_regs(); #ifdef CONFIG_SH_FPU /* can't happen for a kernel thread */ diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index bf4c6addce7b..ecde946ef834 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -319,11 +319,10 @@ extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct thread_info *ti = task_thread_info(p); - struct pt_regs *childregs; + struct pt_regs *childregs, *regs = current_pt_regs(); char *new_stack; #ifndef CONFIG_SMP diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index dff54f46728d..58ef19e7e82f 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -622,10 +622,10 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags, * Child --> %o0 == parents pid, %o1 == 1 */ int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct thread_info *t = task_thread_info(p); + struct pt_regs *regs = current_pt_regs(); struct sparc_stackf *parent_sf; unsigned long child_stack_sz; char *child_trap_frame; diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 267936b51b59..0e5661e7d00d 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -157,10 +157,9 @@ void arch_release_thread_info(struct thread_info *info) static void save_arch_state(struct thread_struct *t); int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { - struct pt_regs *childregs = task_pt_regs(p); + struct pt_regs *childregs = task_pt_regs(p), *regs = current_pt_regs(); unsigned long ksp; unsigned long *callee_regs; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index c502c804e8bb..b462b13c5bae 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -161,8 +161,7 @@ void fork_handler(void) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct * p, - struct pt_regs *regs) + unsigned long arg, struct task_struct * p) { void (*handler)(void); int kthread = current->flags & PF_KTHREAD; diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index 79e44e8ae31c..62bad9fed03e 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -262,7 +262,7 @@ asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p, struct pt_regs *unused) + unsigned long stk_sz, struct task_struct *p) { struct thread_info *thread = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 16efa974532b..b5a8905785e6 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -128,8 +128,7 @@ void release_thread(struct task_struct *dead_task) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 74aac76c6e34..6e68a6194965 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -146,8 +146,7 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { int err; struct pt_regs *childregs; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 0036c14739f8..1accf28da5f5 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -199,8 +199,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) */ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, - unsigned long thread_fn_arg, - struct task_struct *p, struct pt_regs *unused) + unsigned long thread_fn_arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); diff --git a/include/linux/sched.h b/include/linux/sched.h index c57249782e48..78a2ae3470df 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2271,7 +2271,7 @@ extern void mm_release(struct task_struct *, struct mm_struct *); extern struct mm_struct *dup_mm(struct task_struct *tsk); extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *, struct pt_regs *); + struct task_struct *); extern void flush_thread(void); extern void exit_thread(void); diff --git a/kernel/fork.c b/kernel/fork.c index 27a337549dab..d96a562b1311 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1320,7 +1320,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; - retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); + retval = copy_thread(clone_flags, stack_start, stack_size, p); if (retval) goto bad_fork_cleanup_io; -- cgit v1.2.3 From 18c26c27ae0abe82253cb2e2363df465dbbb657e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Oct 2012 22:53:20 -0400 Subject: death to idle_regs() Signed-off-by: Al Viro --- arch/ia64/kernel/smpboot.c | 5 ----- arch/x86/include/asm/processor.h | 2 -- arch/x86/kernel/cpu/common.c | 9 --------- kernel/fork.c | 6 ------ 4 files changed, 22 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 963d2db53bfa..6a368cb2043e 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -460,11 +460,6 @@ start_secondary (void *unused) return 0; } -struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) -{ - return NULL; -} - static int __cpuinit do_boot_cpu (int sapicid, int cpu, struct task_struct *idle) { diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ad1fc8511674..92f48a5a6b2e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -178,8 +178,6 @@ static inline int hlt_works(int cpu) extern void cpu_detect(struct cpuinfo_x86 *c); -extern struct pt_regs *idle_regs(struct pt_regs *); - extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 7505f7b13e71..6a6432cf89de 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1173,15 +1173,6 @@ DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif -/* Make sure %fs and %gs are initialized properly in idle threads */ -struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) -{ - memset(regs, 0, sizeof(struct pt_regs)); - regs->fs = __KERNEL_PERCPU; - regs->gs = __KERNEL_STACK_CANARY; - - return regs; -} #endif /* CONFIG_X86_64 */ /* diff --git a/kernel/fork.c b/kernel/fork.c index fa24a78b94f2..0e68b6686acb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1514,12 +1514,6 @@ fork_out: return ERR_PTR(retval); } -noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs) -{ - memset(regs, 0, sizeof(struct pt_regs)); - return regs; -} - static inline void init_idle_pids(struct pid_link *links) { enum pid_type type; -- cgit v1.2.3 From e5bb8ad862a97a0facc83f3b81731de919fec6ad Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 28 Nov 2012 11:50:26 -0800 Subject: x86, 386 removal: Remove CONFIG_BSWAP All 486+ CPUs support BSWAP, so remove the fallback 386 support code. Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1354132230-21854-5-git-send-email-hpa@linux.intel.com --- arch/x86/Kconfig.cpu | 4 ---- arch/x86/include/asm/futex.h | 12 ------------ arch/x86/include/asm/swab.h | 29 ++--------------------------- arch/x86/kernel/cpu/bugs.c | 13 ++----------- 4 files changed, 4 insertions(+), 54 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 52955eeeb1ef..8e5867cf07d0 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -332,10 +332,6 @@ config X86_INVLPG def_bool y depends on X86_32 -config X86_BSWAP - def_bool y - depends on X86_32 - config X86_POPAD_OK def_bool y depends on X86_32 diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index f373046e63ec..be27ba1e947a 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -55,12 +55,6 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; -#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) - /* Real i386 machines can only support FUTEX_OP_SET */ - if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3) - return -ENOSYS; -#endif - pagefault_disable(); switch (op) { @@ -118,12 +112,6 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, { int ret = 0; -#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) - /* Real i386 machines have no cmpxchg instruction */ - if (boot_cpu_data.x86 == 3) - return -ENOSYS; -#endif - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h index 557cd9f00661..7f235c7105c1 100644 --- a/arch/x86/include/asm/swab.h +++ b/arch/x86/include/asm/swab.h @@ -6,22 +6,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 val) { -#ifdef __i386__ -# ifdef CONFIG_X86_BSWAP - asm("bswap %0" : "=r" (val) : "0" (val)); -# else - asm("xchgb %b0,%h0\n\t" /* swap lower bytes */ - "rorl $16,%0\n\t" /* swap words */ - "xchgb %b0,%h0" /* swap higher bytes */ - : "=q" (val) - : "0" (val)); -# endif - -#else /* __i386__ */ - asm("bswapl %0" - : "=r" (val) - : "0" (val)); -#endif + asm("bswapl %0" : "=r" (val) : "0" (val)); return val; } #define __arch_swab32 __arch_swab32 @@ -37,22 +22,12 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 val) __u64 u; } v; v.u = val; -# ifdef CONFIG_X86_BSWAP asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1" : "=r" (v.s.a), "=r" (v.s.b) : "0" (v.s.a), "1" (v.s.b)); -# else - v.s.a = __arch_swab32(v.s.a); - v.s.b = __arch_swab32(v.s.b); - asm("xchgl %0,%1" - : "=r" (v.s.a), "=r" (v.s.b) - : "0" (v.s.a), "1" (v.s.b)); -# endif return v.u; #else /* __i386__ */ - asm("bswapq %0" - : "=r" (val) - : "0" (val)); + asm("bswapq %0" : "=r" (val) : "0" (val)); return val; #endif } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d0e910da16c5..0cd07ccdf380 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -136,24 +136,15 @@ static void __init check_popad(void) /* * Check whether we are able to run this kernel safely on SMP. * - * - In order to run on a i386, we need to be compiled for i386 - * (for due to lack of "invlpg" and working WP on a i386) + * - i386 is no longer supported. * - In order to run on anything without a TSC, we need to be * compiled for a i486. */ static void __init check_config(void) { -/* - * We'd better not be a i386 if we're configured to use some - * i486+ only features! (WP works in supervisor mode and the - * new "invlpg" and "bswap" instructions) - */ -#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \ - defined(CONFIG_X86_BSWAP) - if (boot_cpu_data.x86 == 3) + if (boot_cpu_data.x86 < 4) panic("Kernel requires i486+ for 'invlpg' and other features"); -#endif } -- cgit v1.2.3 From 094ab1db7cb7833cd4c820acd868fc26acf3f08e Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 28 Nov 2012 11:50:27 -0800 Subject: x86, 386 removal: Remove CONFIG_INVLPG All 486+ CPUs support INVLPG, so remove the fallback 386 support code. Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1354132230-21854-6-git-send-email-hpa@linux.intel.com --- arch/x86/Kconfig.cpu | 4 ---- arch/x86/include/asm/cpufeature.h | 6 ------ arch/x86/include/asm/tlbflush.h | 3 --- arch/x86/kernel/cpu/amd.c | 3 --- arch/x86/kernel/cpu/intel.c | 4 ---- arch/x86/mm/tlb.c | 8 +++----- 6 files changed, 3 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8e5867cf07d0..d3bdc18af1f0 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -328,10 +328,6 @@ config X86_INVD_BUG config X86_WP_WORKS_OK def_bool y -config X86_INVLPG - def_bool y - depends on X86_32 - config X86_POPAD_OK def_bool y depends on X86_32 diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 8c297aa53eef..ff8dd62fda48 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -312,12 +312,6 @@ extern const char * const x86_power_flags[32]; #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) -#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) -# define cpu_has_invlpg 1 -#else -# define cpu_has_invlpg (boot_cpu_data.x86 > 3) -#endif - #ifdef CONFIG_X86_64 #undef cpu_has_vme diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 74a44333545a..0fee48e279cc 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -56,10 +56,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - if (cpu_has_invlpg) __flush_tlb_single(addr); - else - __flush_tlb(); } #define TLB_FLUSH_ALL -1UL diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1b7d1656a042..a025d8cc4577 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -753,9 +753,6 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { - if (!cpu_has_invlpg) - return; - tlb_flushall_shift = 5; if (c->x86 <= 0x11) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 198e019a531a..fcaabd0432c5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -612,10 +612,6 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) { - if (!cpu_has_invlpg) { - tlb_flushall_shift = -1; - return; - } switch ((c->x86 << 8) + c->x86_model) { case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 60f926cd8b0e..13a6b29e2e5d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -104,7 +104,7 @@ static void flush_tlb_func(void *info) return; if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL || !cpu_has_invlpg) + if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); else if (!f->flush_end) __flush_tlb_single(f->flush_start); @@ -337,10 +337,8 @@ static const struct file_operations fops_tlbflush = { static int __cpuinit create_tlb_flushall_shift(void) { - if (cpu_has_invlpg) { - debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR, - arch_debugfs_dir, NULL, &fops_tlbflush); - } + debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR, + arch_debugfs_dir, NULL, &fops_tlbflush); return 0; } late_initcall(create_tlb_flushall_shift); -- cgit v1.2.3 From e3228cf4544355f73437a2b9c6916be9cbafc201 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 28 Nov 2012 11:50:29 -0800 Subject: x86, 386 removal: Remove CONFIG_X86_POPAD_OK The check_popad() routine tested for a 386-specific bug, and never actually did anything useful with it anyway other than print a message. Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1354132230-21854-8-git-send-email-hpa@linux.intel.com --- arch/x86/Kconfig.cpu | 4 ---- arch/x86/kernel/cpu/bugs.c | 28 ---------------------------- 2 files changed, 32 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 159ee9c824c9..423db7189eb9 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -325,10 +325,6 @@ config X86_INVD_BUG def_bool y depends on M486 -config X86_POPAD_OK - def_bool y - depends on X86_32 - config X86_ALIGNMENT_16 def_bool y depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0cd07ccdf380..92dfec986a48 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -106,33 +106,6 @@ static void __init check_hlt(void) pr_cont("OK\n"); } -/* - * Most 386 processors have a bug where a POPAD can lock the - * machine even from user space. - */ - -static void __init check_popad(void) -{ -#ifndef CONFIG_X86_POPAD_OK - int res, inp = (int) &res; - - pr_info("Checking for popad bug... "); - __asm__ __volatile__( - "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " - : "=&a" (res) - : "d" (inp) - : "ecx", "edi"); - /* - * If this fails, it means that any user program may lock the - * CPU hard. Too bad. - */ - if (res != 12345678) - pr_cont("Buggy\n"); - else - pr_cont("OK\n"); -#endif -} - /* * Check whether we are able to run this kernel safely on SMP. * @@ -157,7 +130,6 @@ void __init check_bugs(void) #endif check_config(); check_hlt(); - check_popad(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); -- cgit v1.2.3 From 91d1aa43d30505b0b825db8898ffc80a8eca96c7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 27 Nov 2012 19:33:25 +0100 Subject: context_tracking: New context tracking susbsystem Create a new subsystem that probes on kernel boundaries to keep track of the transitions between level contexts with two basic initial contexts: user or kernel. This is an abstraction of some RCU code that use such tracking to implement its userspace extended quiescent state. We need to pull this up from RCU into this new level of indirection because this tracking is also going to be used to implement an "on demand" generic virtual cputime accounting. A necessary step to shutdown the tick while still accounting the cputime. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Li Zhong Cc: Gilad Ben-Yossef Reviewed-by: Steven Rostedt [ paulmck: fix whitespace error and email address. ] Signed-off-by: Paul E. McKenney --- arch/Kconfig | 15 +++--- arch/x86/Kconfig | 2 +- arch/x86/include/asm/context_tracking.h | 31 ++++++++++++ arch/x86/include/asm/rcu.h | 32 ------------- arch/x86/kernel/entry_64.S | 2 +- arch/x86/kernel/ptrace.c | 8 ++-- arch/x86/kernel/signal.c | 5 +- arch/x86/kernel/traps.c | 2 +- arch/x86/mm/fault.c | 2 +- include/linux/context_tracking.h | 18 +++++++ include/linux/rcupdate.h | 2 - init/Kconfig | 28 +++++------ kernel/Makefile | 1 + kernel/context_tracking.c | 83 +++++++++++++++++++++++++++++++++ kernel/rcutree.c | 64 +------------------------ kernel/sched/core.c | 11 +++-- 16 files changed, 174 insertions(+), 132 deletions(-) create mode 100644 arch/x86/include/asm/context_tracking.h delete mode 100644 arch/x86/include/asm/rcu.h create mode 100644 include/linux/context_tracking.h create mode 100644 kernel/context_tracking.c (limited to 'arch/x86/kernel') diff --git a/arch/Kconfig b/arch/Kconfig index 366ec06a5185..cc74aaea116c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -300,15 +300,16 @@ config SECCOMP_FILTER See Documentation/prctl/seccomp_filter.txt for details. -config HAVE_RCU_USER_QS +config HAVE_CONTEXT_TRACKING bool help - Provide kernel entry/exit hooks necessary for userspace - RCU extended quiescent state. Syscalls need to be wrapped inside - rcu_user_exit()-rcu_user_enter() through the slow path using - TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs - are already protected inside rcu_irq_enter/rcu_irq_exit() but - preemption or signal handling on irq exit still need to be protected. + Provide kernel/user boundaries probes necessary for subsystems + that need it, such as userspace RCU extended quiescent state. + Syscalls need to be wrapped inside user_exit()-user_enter() through + the slow path using TIF_NOHZ flag. Exceptions handlers must be + wrapped as well. Irqs are already protected inside + rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on + irq exit still need to be protected. config HAVE_VIRT_CPU_ACCOUNTING bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 46c3bff3ced2..110cfad24f26 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -106,7 +106,7 @@ config X86 select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER - select HAVE_RCU_USER_QS if X86_64 + select HAVE_CONTEXT_TRACKING if X86_64 select HAVE_IRQ_TIME_ACCOUNTING select GENERIC_KERNEL_THREAD select GENERIC_KERNEL_EXECVE diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h new file mode 100644 index 000000000000..1616562683e9 --- /dev/null +++ b/arch/x86/include/asm/context_tracking.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_CONTEXT_TRACKING_H +#define _ASM_X86_CONTEXT_TRACKING_H + +#ifndef __ASSEMBLY__ +#include +#include + +static inline void exception_enter(struct pt_regs *regs) +{ + user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ +#ifdef CONFIG_CONTEXT_TRACKING + if (user_mode(regs)) + user_enter(); +#endif +} + +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_CONTEXT_TRACKING +# define SCHEDULE_USER call schedule_user +#else +# define SCHEDULE_USER call schedule +#endif + +#endif /* !__ASSEMBLY__ */ + +#endif diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h deleted file mode 100644 index d1ac07a23979..000000000000 --- a/arch/x86/include/asm/rcu.h +++ /dev/null @@ -1,32 +0,0 @@ -#ifndef _ASM_X86_RCU_H -#define _ASM_X86_RCU_H - -#ifndef __ASSEMBLY__ - -#include -#include - -static inline void exception_enter(struct pt_regs *regs) -{ - rcu_user_exit(); -} - -static inline void exception_exit(struct pt_regs *regs) -{ -#ifdef CONFIG_RCU_USER_QS - if (user_mode(regs)) - rcu_user_enter(); -#endif -} - -#else /* __ASSEMBLY__ */ - -#ifdef CONFIG_RCU_USER_QS -# define SCHEDULE_USER call schedule_user -#else -# define SCHEDULE_USER call schedule -#endif - -#endif /* !__ASSEMBLY__ */ - -#endif diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 0c58952d64e8..98faeb30139d 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,7 +56,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index eff5b8c68652..65b88a5dc1a8 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include @@ -1461,7 +1461,7 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - rcu_user_exit(); + user_exit(); /* * If we stepped into a sysenter/syscall insn, it trapped in @@ -1516,7 +1516,7 @@ void syscall_trace_leave(struct pt_regs *regs) * or do_notify_resume(), in which case we can be in RCU * user mode. */ - rcu_user_exit(); + user_exit(); audit_syscall_exit(regs); @@ -1534,5 +1534,5 @@ void syscall_trace_leave(struct pt_regs *regs) if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); - rcu_user_enter(); + user_enter(); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 29ad351804e9..20ecac112e74 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -816,7 +817,7 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { - rcu_user_exit(); + user_exit(); #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ @@ -840,7 +841,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) fire_user_return_notifiers(); - rcu_user_enter(); + user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8276dc6794cc..eb8586693e0b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,7 +55,7 @@ #include #include #include -#include +#include #include diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8e13ecb41bee..7a529cbab7ad 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,7 +18,7 @@ #include /* pgd_*(), ... */ #include /* kmemcheck_*(), ... */ #include /* VSYSCALL_START */ -#include /* exception_enter(), ... */ +#include /* exception_enter(), ... */ /* * Page fault error code bits: diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h new file mode 100644 index 000000000000..e24339ccb7f0 --- /dev/null +++ b/include/linux/context_tracking.h @@ -0,0 +1,18 @@ +#ifndef _LINUX_CONTEXT_TRACKING_H +#define _LINUX_CONTEXT_TRACKING_H + +#ifdef CONFIG_CONTEXT_TRACKING +#include + +extern void user_enter(void); +extern void user_exit(void); +extern void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next); +#else +static inline void user_enter(void) { } +static inline void user_exit(void) { } +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) { } +#endif /* !CONFIG_CONTEXT_TRACKING */ + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8fe7c1840d30..275aa3f1062d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -222,8 +222,6 @@ extern void rcu_user_enter(void); extern void rcu_user_exit(void); extern void rcu_user_enter_after_irq(void); extern void rcu_user_exit_after_irq(void); -extern void rcu_user_hooks_switch(struct task_struct *prev, - struct task_struct *next); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } diff --git a/init/Kconfig b/init/Kconfig index 5ac6ee094225..2054e048bb98 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -486,9 +486,13 @@ config PREEMPT_RCU This option enables preemptible-RCU code that is common between the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. +config CONTEXT_TRACKING + bool + config RCU_USER_QS bool "Consider userspace as in RCU extended quiescent state" - depends on HAVE_RCU_USER_QS && SMP + depends on HAVE_CONTEXT_TRACKING && SMP + select CONTEXT_TRACKING help This option sets hooks on kernel / userspace boundaries and puts RCU in extended quiescent state when the CPU runs in @@ -497,24 +501,20 @@ config RCU_USER_QS try to keep the timer tick on for RCU. Unless you want to hack and help the development of the full - tickless feature, you shouldn't enable this option. It also + dynticks mode, you shouldn't enable this option. It also adds unnecessary overhead. If unsure say N -config RCU_USER_QS_FORCE - bool "Force userspace extended QS by default" - depends on RCU_USER_QS +config CONTEXT_TRACKING_FORCE + bool "Force context tracking" + depends on CONTEXT_TRACKING help - Set the hooks in user/kernel boundaries by default in order to - test this feature that treats userspace as an extended quiescent - state until we have a real user like a full adaptive nohz option. - - Unless you want to hack and help the development of the full - tickless feature, you shouldn't enable this option. It adds - unnecessary overhead. - - If unsure say N + Probe on user/kernel boundaries by default in order to + test the features that rely on it such as userspace RCU extended + quiescent states. + This test is there for debugging until we have a real user like the + full dynticks mode. config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" diff --git a/kernel/Makefile b/kernel/Makefile index 0dfeca4324ee..f90bbfc9727f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -110,6 +110,7 @@ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o obj-$(CONFIG_PADATA) += padata.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c new file mode 100644 index 000000000000..e0e07fd55508 --- /dev/null +++ b/kernel/context_tracking.c @@ -0,0 +1,83 @@ +#include +#include +#include +#include +#include + +struct context_tracking { + /* + * When active is false, hooks are not set to + * minimize overhead: TIF flags are cleared + * and calls to user_enter/exit are ignored. This + * may be further optimized using static keys. + */ + bool active; + enum { + IN_KERNEL = 0, + IN_USER, + } state; +}; + +static DEFINE_PER_CPU(struct context_tracking, context_tracking) = { +#ifdef CONFIG_CONTEXT_TRACKING_FORCE + .active = true, +#endif +}; + +void user_enter(void) +{ + unsigned long flags; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + WARN_ON_ONCE(!current->mm); + + local_irq_save(flags); + if (__this_cpu_read(context_tracking.active) && + __this_cpu_read(context_tracking.state) != IN_USER) { + __this_cpu_write(context_tracking.state, IN_USER); + rcu_user_enter(); + } + local_irq_restore(flags); +} + +void user_exit(void) +{ + unsigned long flags; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + local_irq_save(flags); + if (__this_cpu_read(context_tracking.state) == IN_USER) { + __this_cpu_write(context_tracking.state, IN_KERNEL); + rcu_user_exit(); + } + local_irq_restore(flags); +} + +void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) +{ + if (__this_cpu_read(context_tracking.active)) { + clear_tsk_thread_flag(prev, TIF_NOHZ); + set_tsk_thread_flag(next, TIF_NOHZ); + } +} diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 7733eb56e156..e441b77b614e 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -207,9 +207,6 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), -#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE) - .ignore_user_qs = true, -#endif }; static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ @@ -420,29 +417,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter); */ void rcu_user_enter(void) { - unsigned long flags; - struct rcu_dynticks *rdtp; - - /* - * Some contexts may involve an exception occuring in an irq, - * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() - * This would mess up the dyntick_nesting count though. And rcu_irq_*() - * helpers are enough to protect RCU uses inside the exception. So - * just return immediately if we detect we are in an IRQ. - */ - if (in_interrupt()) - return; - - WARN_ON_ONCE(!current->mm); - - local_irq_save(flags); - rdtp = &__get_cpu_var(rcu_dynticks); - if (!rdtp->ignore_user_qs && !rdtp->in_user) { - rdtp->in_user = true; - rcu_eqs_enter(true); - } - local_irq_restore(flags); + rcu_eqs_enter(1); } /** @@ -579,27 +554,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit); */ void rcu_user_exit(void) { - unsigned long flags; - struct rcu_dynticks *rdtp; - - /* - * Some contexts may involve an exception occuring in an irq, - * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() - * This would mess up the dyntick_nesting count though. And rcu_irq_*() - * helpers are enough to protect RCU uses inside the exception. So - * just return immediately if we detect we are in an IRQ. - */ - if (in_interrupt()) - return; - - local_irq_save(flags); - rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->in_user) { - rdtp->in_user = false; - rcu_eqs_exit(true); - } - local_irq_restore(flags); + rcu_eqs_exit(1); } /** @@ -722,21 +677,6 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_RCU_USER_QS -void rcu_user_hooks_switch(struct task_struct *prev, - struct task_struct *next) -{ - struct rcu_dynticks *rdtp; - - /* Interrupts are disabled in context switch */ - rdtp = &__get_cpu_var(rcu_dynticks); - if (!rdtp->ignore_user_qs) { - clear_tsk_thread_flag(prev, TIF_NOHZ); - set_tsk_thread_flag(next, TIF_NOHZ); - } -} -#endif /* #ifdef CONFIG_RCU_USER_QS */ - #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 36f260864f65..80f80dfca70e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include @@ -1886,8 +1887,8 @@ context_switch(struct rq *rq, struct task_struct *prev, spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #endif + context_tracking_task_switch(prev, next); /* Here we just switch the register state and the stack. */ - rcu_user_hooks_switch(prev, next); switch_to(prev, next, prev); barrier(); @@ -2911,7 +2912,7 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); -#ifdef CONFIG_RCU_USER_QS +#ifdef CONFIG_CONTEXT_TRACKING asmlinkage void __sched schedule_user(void) { /* @@ -2920,9 +2921,9 @@ asmlinkage void __sched schedule_user(void) * we haven't yet exited the RCU idle mode. Do it here manually until * we find a better solution. */ - rcu_user_exit(); + user_exit(); schedule(); - rcu_user_enter(); + user_enter(); } #endif @@ -3027,7 +3028,7 @@ asmlinkage void __sched preempt_schedule_irq(void) /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); - rcu_user_exit(); + user_exit(); do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); -- cgit v1.2.3 From 644c154186386bb1fa6446bc5e037b9ed098db46 Mon Sep 17 00:00:00 2001 From: Vincent Palatin Date: Fri, 30 Nov 2012 12:15:32 -0800 Subject: x86, fpu: Avoid FPU lazy restore after suspend When a cpu enters S3 state, the FPU state is lost. After resuming for S3, if we try to lazy restore the FPU for a process running on the same CPU, this will result in a corrupted FPU context. Ensure that "fpu_owner_task" is properly invalided when (re-)initializing a CPU, so nobody will try to lazy restore a state which doesn't exist in the hardware. Tested with a 64-bit kernel on a 4-core Ivybridge CPU with eagerfpu=off, by doing thousands of suspend/resume cycles with 4 processes doing FPU operations running. Without the patch, a process is killed after a few hundreds cycles by a SIGFPE. Cc: Duncan Laurie Cc: Olof Johansson Cc: v3.4+ # for 3.4 need to replace this_cpu_write by percpu_write Signed-off-by: Vincent Palatin Link: http://lkml.kernel.org/r/1354306532-1014-1-git-send-email-vpalatin@chromium.org Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/fpu-internal.h | 15 +++++++++------ arch/x86/kernel/smpboot.c | 5 +++++ 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 831dbb9c6c02..41ab26ea6564 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk) typedef struct { int preload; } fpu_switch_t; /* - * FIXME! We could do a totally lazy restore, but we need to - * add a per-cpu "this was the task that last touched the FPU - * on this CPU" variable, and the task needs to have a "I last - * touched the FPU on this CPU" and check them. + * Must be run with preemption disabled: this clears the fpu_owner_task, + * on this CPU. * - * We don't do that yet, so "fpu_lazy_restore()" always returns - * false, but some day.. + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_owner_task, cpu) = NULL; +} + static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) { return new == this_cpu_read_stable(fpu_owner_task) && diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c80a33bc528b..f3e2ec878b8c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,6 +68,8 @@ #include #include #include +#include +#include #include #include #include @@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* the FPU context is blank, nobody can own it */ + __cpu_disable_lazy_restore(cpu); + err = do_boot_cpu(apicid, cpu, tidle); if (err) { pr_debug("do_boot_cpu failed %d\n", err); -- cgit v1.2.3 From f9a37be0f02a943d63e3346b19f9c9d8d91826cb Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 5 Dec 2012 14:33:27 -0700 Subject: x86: Use PCI setup data EFI can provide PCI ROMs out of band via boot services, which may not be available after boot. Add support for using the data handed off to us by the boot stub or bootloader. [bhelgaas: added Seth's boot_params section mismatch fix] [bhelgaas: drop "boot_params.hdr.version < 0x0209" test] Signed-off-by: Matthew Garrett Signed-off-by: Bjorn Helgaas Tested-by: Seth Forshee --- arch/x86/kernel/setup.c | 4 ---- arch/x86/pci/common.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ca45696f30fb..c228322ca180 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -143,11 +143,7 @@ int default_check_phys_apicid_present(int phys_apicid) } #endif -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else struct boot_params boot_params; -#endif /* * Machine setup.. diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 720e973fc34a..fddb9f66cc47 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -17,6 +17,7 @@ #include #include #include +#include unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; @@ -608,6 +609,35 @@ unsigned int pcibios_assign_all_busses(void) return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0; } +int pcibios_add_device(struct pci_dev *dev) +{ + struct setup_data *data; + struct pci_setup_rom *rom; + u64 pa_data; + + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = phys_to_virt(pa_data); + + if (data->type == SETUP_PCI) { + rom = (struct pci_setup_rom *)data; + + if ((pci_domain_nr(dev->bus) == rom->segment) && + (dev->bus->number == rom->bus) && + (PCI_SLOT(dev->devfn) == rom->device) && + (PCI_FUNC(dev->devfn) == rom->function) && + (dev->vendor == rom->vendor) && + (dev->device == rom->devid)) { + dev->rom = (void *)(unsigned long)(pa_data + + offsetof(struct pci_setup_rom, romdata)); + dev->romlen = rom->pcilen; + } + } + pa_data = data->next; + } + return 0; +} + int pcibios_enable_device(struct pci_dev *dev, int mask) { int err; -- cgit v1.2.3 From f23d1f4a116038c68df224deae6718fde87d8f0d Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Thu, 6 Dec 2012 23:40:47 +0800 Subject: x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary This patch provides a way to VMCLEAR VMCSs related to guests on all cpus before executing the VMXOFF when doing kdump. This is used to ensure the VMCSs in the vmcore updated and non-corrupted. Signed-off-by: Zhang Yanfei Acked-by: Eric W. Biederman Signed-off-by: Gleb Natapov --- arch/x86/include/asm/kexec.h | 2 ++ arch/x86/kernel/crash.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 317ff1703d0b..28feeba2fdd6 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -163,6 +163,8 @@ struct kimage_arch { }; #endif +extern void (*crash_vmclear_loaded_vmcss)(void); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_KEXEC_H */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 13ad89971d47..2f6b8e838d18 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -30,6 +31,27 @@ int in_crash_kexec; +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +void (*crash_vmclear_loaded_vmcss)(void) = NULL; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); + +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + void (*do_vmclear_operation)(void) = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -46,6 +68,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) #endif crash_save_cpu(regs, cpu); + /* + * VMCLEAR VMCSs loaded on all cpus if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Disable VMX or SVM if needed. * * We need to disable virtualization on all CPUs. @@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) kdump_nmi_shootdown_cpus(); + /* + * VMCLEAR VMCSs loaded on this cpu if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Booting kdump kernel with VMX or SVM enabled won't work, * because (among other limitations) we can't disable paging * with the virt flags. -- cgit v1.2.3 From 4319eb4fc7196536c751f9e8a273759b3298c10b Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Thu, 6 Dec 2012 21:16:11 +0100 Subject: x86 mtrr: fix comment typo in mtrr_bp_init Signed-off-by: Olaf Hering Signed-off-by: Jiri Kosina --- arch/x86/kernel/cpu/mtrr/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6b96110bb0c3..b5a0fd891d73 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -606,7 +606,7 @@ void __init mtrr_bp_init(void) /* * This is an AMD specific MSR, but we assume(hope?) that - * Intel will implement it to when they extend the address + * Intel will implement it too when they extend the address * bus of the Xeon. */ if (cpuid_eax(0x80000000) >= 0x80000008) { -- cgit v1.2.3 From f9726bfd4b14401d294207a70c7c0c4be8a8c6cc Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Fri, 7 Dec 2012 14:24:32 -0700 Subject: x86/PCI: Add NumaChip remote PCI support Add NumaChip-specific PCI access mechanism via MMCONFIG cycles, but preventing access to AMD Northbridges which shouldn't respond. Signed-off-by: Daniel J Blueman Signed-off-by: Bjorn Helgaas --- arch/x86/Kconfig | 1 + arch/x86/include/asm/numachip/numachip.h | 19 +++++ arch/x86/kernel/apic/apic_numachip.c | 2 + arch/x86/pci/Makefile | 1 + arch/x86/pci/numachip.c | 129 +++++++++++++++++++++++++++++++ 5 files changed, 152 insertions(+) create mode 100644 arch/x86/include/asm/numachip/numachip.h create mode 100644 arch/x86/pci/numachip.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 46c3bff3ced2..17fb8eb3fa6b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -374,6 +374,7 @@ config X86_NUMACHIP depends on NUMA depends on SMP depends on X86_X2APIC + depends on PCI_MMCONFIG ---help--- Adds support for Numascale NumaChip large-SMP systems. Needed to enable more than ~168 cores. diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h new file mode 100644 index 000000000000..1c6f7f6212c1 --- /dev/null +++ b/arch/x86/include/asm/numachip/numachip.h @@ -0,0 +1,19 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-specific header file + * + * Copyright (C) 2012 Numascale AS. All rights reserved. + * + * Send feedback to + * + */ + +#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H +#define _ASM_X86_NUMACHIP_NUMACHIP_H + +extern int __init pci_numachip_init(void); + +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */ diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index a65829ac2b9a..9c2aa89a11cb 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -179,6 +180,7 @@ static int __init numachip_system_init(void) return 0; x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; map_csrs(); diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 3af5a1e79c9c..ee0af58ca5bd 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_STA2X11) += sta2x11-fixup.o obj-$(CONFIG_X86_VISWS) += visws.o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o +obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_X86_INTEL_MID) += mrst.o diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c new file mode 100644 index 000000000000..7307d9d12d15 --- /dev/null +++ b/arch/x86/pci/numachip.c @@ -0,0 +1,129 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-specific PCI code + * + * Copyright (C) 2012 Numascale AS. All rights reserved. + * + * Send feedback to + * + * PCI accessor functions derived from mmconfig_64.c + * + */ + +#include +#include + +static u8 limit __read_mostly; + +static inline char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn) +{ + struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus); + + if (cfg && cfg->virt) + return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12)); + return NULL; +} + +static int pci_mmcfg_read_numachip(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 *value) +{ + char __iomem *addr; + + /* Why do we have this when nobody checks it. How about a BUG()!? -AK */ + if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) { +err: *value = -1; + return -EINVAL; + } + + /* Ensure AMD Northbridges don't decode reads to other devices */ + if (unlikely(bus == 0 && devfn >= limit)) { + *value = -1; + return 0; + } + + rcu_read_lock(); + addr = pci_dev_base(seg, bus, devfn); + if (!addr) { + rcu_read_unlock(); + goto err; + } + + switch (len) { + case 1: + *value = mmio_config_readb(addr + reg); + break; + case 2: + *value = mmio_config_readw(addr + reg); + break; + case 4: + *value = mmio_config_readl(addr + reg); + break; + } + rcu_read_unlock(); + + return 0; +} + +static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 value) +{ + char __iomem *addr; + + /* Why do we have this when nobody checks it. How about a BUG()!? -AK */ + if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) + return -EINVAL; + + /* Ensure AMD Northbridges don't decode writes to other devices */ + if (unlikely(bus == 0 && devfn >= limit)) + return 0; + + rcu_read_lock(); + addr = pci_dev_base(seg, bus, devfn); + if (!addr) { + rcu_read_unlock(); + return -EINVAL; + } + + switch (len) { + case 1: + mmio_config_writeb(addr + reg, value); + break; + case 2: + mmio_config_writew(addr + reg, value); + break; + case 4: + mmio_config_writel(addr + reg, value); + break; + } + rcu_read_unlock(); + + return 0; +} + +const struct pci_raw_ops pci_mmcfg_numachip = { + .read = pci_mmcfg_read_numachip, + .write = pci_mmcfg_write_numachip, +}; + +int __init pci_numachip_init(void) +{ + int ret = 0; + u32 val; + + /* For remote I/O, restrict bus 0 access to the actual number of AMD + Northbridges, which starts at device number 0x18 */ + ret = raw_pci_read(0, 0, PCI_DEVFN(0x18, 0), 0x60, sizeof(val), &val); + if (ret) + goto out; + + /* HyperTransport fabric size in bits 6:4 */ + limit = PCI_DEVFN(0x18 + ((val >> 4) & 7) + 1, 0); + + /* Use NumaChip PCI accessors for non-extended and extended access */ + raw_pci_ops = raw_pci_ext_ops = &pci_mmcfg_numachip; +out: + return ret; +} -- cgit v1.2.3 From 0ca0d818cbcbcac75a02833861b6fc42a98b904e Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Tue, 11 Dec 2012 17:11:34 +0800 Subject: x86/kexec: crash_vmclear_local_vmcss needs __rcu This removes the sparse warning: arch/x86/kernel/crash.c:49:32: sparse: incompatible types in comparison expression (different address spaces) Reported-by: kbuild test robot Signed-off-by: Zhang Yanfei Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kexec.h | 3 ++- arch/x86/kernel/crash.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 28feeba2fdd6..6080d2694bad 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -163,7 +163,8 @@ struct kimage_arch { }; #endif -extern void (*crash_vmclear_loaded_vmcss)(void); +typedef void crash_vmclear_fn(void); +extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2f6b8e838d18..74467feb4dc5 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -38,12 +38,12 @@ int in_crash_kexec; * * protected by rcu. */ -void (*crash_vmclear_loaded_vmcss)(void) = NULL; +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); static inline void cpu_crash_vmclear_loaded_vmcss(void) { - void (*do_vmclear_operation)(void) = NULL; + crash_vmclear_fn *do_vmclear_operation = NULL; rcu_read_lock(); do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); -- cgit v1.2.3 From f99024729e689f5de4534fde5400e3b035f068de Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Tue, 11 Dec 2012 16:01:52 -0800 Subject: mm: use vm_unmapped_area() on x86_64 architecture Update the x86_64 arch_get_unmapped_area[_topdown] functions to make use of vm_unmapped_area() instead of implementing a brute force search. Signed-off-by: Michel Lespinasse Reviewed-by: Rik van Riel Cc: Hugh Dickins Cc: Russell King Cc: Ralf Baechle Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/elf.h | 6 +- arch/x86/kernel/sys_x86_64.c | 151 +++++++++---------------------------------- arch/x86/vdso/vma.c | 2 +- 3 files changed, 33 insertions(+), 126 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 5939f44fe0c0..9c999c1674fa 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -354,12 +354,10 @@ static inline int mmap_is_ia32(void) return 0; } -/* The first two values are special, do not change. See align_addr() */ +/* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), ALIGN_VA_64 = BIT(1), - ALIGN_VDSO = BIT(2), - ALIGN_TOPDOWN = BIT(3), }; struct va_alignment { @@ -368,5 +366,5 @@ struct va_alignment { } ____cacheline_aligned; extern struct va_alignment va_align; -extern unsigned long align_addr(unsigned long, struct file *, enum align_flags); +extern unsigned long align_vdso_addr(unsigned long); #endif /* _ASM_X86_ELF_H */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index b4d3c3927dd8..f00d006d60fd 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,37 +21,23 @@ /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. - * - * @flags denotes the allocation direction - bottomup or topdown - - * or vDSO; see call sites below. */ -unsigned long align_addr(unsigned long addr, struct file *filp, - enum align_flags flags) +static unsigned long get_align_mask(void) { - unsigned long tmp_addr; - /* handle 32- and 64-bit case with a single conditional */ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) - return addr; + return 0; if (!(current->flags & PF_RANDOMIZE)) - return addr; - - if (!((flags & ALIGN_VDSO) || filp)) - return addr; - - tmp_addr = addr; - - /* - * We need an address which is <= than the original - * one only when in topdown direction. - */ - if (!(flags & ALIGN_TOPDOWN)) - tmp_addr += va_align.mask; + return 0; - tmp_addr &= ~va_align.mask; + return va_align.mask; +} - return tmp_addr; +unsigned long align_vdso_addr(unsigned long addr) +{ + unsigned long align_mask = get_align_mask(); + return (addr + align_mask) & ~align_mask; } static int __init control_va_addr_alignment(char *str) @@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long start_addr; + struct vm_unmapped_area_info info; unsigned long begin, end; if (flags & MAP_FIXED) @@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) - && len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = begin; - } - addr = mm->free_area_cache; - if (addr < begin) - addr = begin; - start_addr = addr; - -full_search: - - addr = align_addr(addr, filp, 0); - - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (end - len < addr) { - /* - * Start a new search - just in case we missed - * some holes. - */ - if (start_addr != begin) { - start_addr = addr = begin; - mm->cached_hole_size = 0; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - mm->free_area_cache = addr + len; - return addr; - } - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - addr = align_addr(addr, filp, 0); - } + info.flags = 0; + info.length = len; + info.low_limit = begin; + info.high_limit = end; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = 0; + return vm_unmapped_area(&info); } - unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, @@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - unsigned long addr = addr0, start_addr; + unsigned long addr = addr0; + struct vm_unmapped_area_info info; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; } - /* check if free_area_cache is useful for us */ - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - -try_again: - /* either no address requested or can't fit in requested address hole */ - start_addr = addr = mm->free_area_cache; - - if (addr < len) - goto fail; - - addr -= len; - do { - addr = align_addr(addr, filp, ALIGN_TOPDOWN); - - /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: - */ - vma = find_vma(mm, addr); - if (!vma || addr+len <= vma->vm_start) - /* remember the address as a hint for next time */ - return mm->free_area_cache = addr; - - /* remember the largest hole we saw so far */ - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; - } while (len < vma->vm_start); - -fail: - /* - * if hint left us with no space for the requested - * mapping then try again: - */ - if (start_addr != mm->mmap_base) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = 0; - goto try_again; - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = 0; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); bottomup: /* @@ -270,14 +188,5 @@ bottomup: * can happen with large stack limits and large mmap() * allocations. */ - mm->cached_hole_size = ~0UL; - mm->free_area_cache = TASK_UNMAPPED_BASE; - addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - /* - * Restore the topdown base: - */ - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - - return addr; + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 00aaf047b39f..431e87544411 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -141,7 +141,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) * unaligned here as a result of stack start randomization. */ addr = PAGE_ALIGN(addr); - addr = align_addr(addr, NULL, ALIGN_VDSO); + addr = align_vdso_addr(addr); return addr; } -- cgit v1.2.3 From 7d025059650f1c41a427173789ac14b74212b361 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Tue, 11 Dec 2012 16:01:56 -0800 Subject: mm: fix cache coloring on x86_64 architecture Fix the x86-64 cache alignment code to take pgoff into account. Use the x86 and MIPS cache alignment code as the basis for a generic cache alignment function. The old x86 code will always align the mmap to aliasing boundaries, even if the program mmaps the file with a non-zero pgoff. If program A mmaps the file with pgoff 0, and program B mmaps the file with pgoff 1. The old code would align the mmaps, resulting in misaligned pages: A: 0123 B: 123 After this patch, they are aligned so the pages line up: A: 0123 B: 123 Proposed by Rik van Riel. Signed-off-by: Michel Lespinasse Cc: Rik van Riel Cc: Hugh Dickins Cc: Russell King Cc: Ralf Baechle Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/sys_x86_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index f00d006d60fd..97ef74b88e0f 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -136,7 +136,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = begin; info.high_limit = end; info.align_mask = filp ? get_align_mask() : 0; - info.align_offset = 0; + info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } @@ -175,7 +175,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; info.align_mask = filp ? get_align_mask() : 0; - info.align_offset = 0; + info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); if (!(addr & ~PAGE_MASK)) return addr; -- cgit v1.2.3 From e180377f1ae48b3cbc559c9875d9b038f7f000c6 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 12 Dec 2012 13:50:59 -0800 Subject: thp: change split_huge_page_pmd() interface Pass vma instead of mm and add address parameter. In most cases we already have vma on the stack. We provides split_huge_page_pmd_mm() for few cases when we have mm, but not vma. This change is preparation to huge zero pmd splitting implementation. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Andi Kleen Cc: "H. Peter Anvin" Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/transhuge.txt | 4 ++-- arch/x86/kernel/vm86_32.c | 2 +- fs/proc/task_mmu.c | 2 +- include/linux/huge_mm.h | 14 ++++++++++---- mm/huge_memory.c | 19 +++++++++++++++++-- mm/memory.c | 4 ++-- mm/mempolicy.c | 2 +- mm/mprotect.c | 2 +- mm/mremap.c | 2 +- mm/pagewalk.c | 2 +- 10 files changed, 37 insertions(+), 16 deletions(-) (limited to 'arch/x86/kernel') diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt index f734bb2a78dc..8f5b41db314c 100644 --- a/Documentation/vm/transhuge.txt +++ b/Documentation/vm/transhuge.txt @@ -276,7 +276,7 @@ unaffected. libhugetlbfs will also work fine as usual. == Graceful fallback == Code walking pagetables but unware about huge pmds can simply call -split_huge_page_pmd(mm, pmd) where the pmd is the one returned by +split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by pmd_offset. It's trivial to make the code transparent hugepage aware by just grepping for "pmd_offset" and adding split_huge_page_pmd where missing after pmd_offset returns the pmd. Thanks to the graceful @@ -299,7 +299,7 @@ diff --git a/mm/mremap.c b/mm/mremap.c return NULL; pmd = pmd_offset(pud, addr); -+ split_huge_page_pmd(mm, pmd); ++ split_huge_page_pmd(vma, addr, pmd); if (pmd_none_or_clear_bad(pmd)) return NULL; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 5c9687b1bde6..1dfe69cc78a8 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd_mm(mm, 0xA0000, pmd); if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 90c63f9392a5..291a0d15a0be 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -643,7 +643,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - split_huge_page_pmd(walk->mm, pmd); + split_huge_page_pmd(vma, addr, pmd); if (pmd_trans_unstable(pmd)) return 0; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1af477552459..3132ea788581 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -95,12 +95,14 @@ extern int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags); extern int split_huge_page(struct page *page); -extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); -#define split_huge_page_pmd(__mm, __pmd) \ +extern void __split_huge_page_pmd(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd); +#define split_huge_page_pmd(__vma, __address, __pmd) \ do { \ pmd_t *____pmd = (__pmd); \ if (unlikely(pmd_trans_huge(*____pmd))) \ - __split_huge_page_pmd(__mm, ____pmd); \ + __split_huge_page_pmd(__vma, __address, \ + ____pmd); \ } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { \ @@ -110,6 +112,8 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) +extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, + pmd_t *pmd); #if HPAGE_PMD_ORDER > MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -177,10 +181,12 @@ static inline int split_huge_page(struct page *page) { return 0; } -#define split_huge_page_pmd(__mm, __pmd) \ +#define split_huge_page_pmd(__vma, __address, __pmd) \ do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) +#define split_huge_page_pmd_mm(__mm, __address, __pmd) \ + do { } while (0) #define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7742fb36eb4d..de6aa5f3fdd2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2475,9 +2475,14 @@ static int khugepaged(void *none) return 0; } -void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd) +void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd) { struct page *page; + unsigned long haddr = address & HPAGE_PMD_MASK; + struct mm_struct *mm = vma->vm_mm; + + BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE); spin_lock(&mm->page_table_lock); if (unlikely(!pmd_trans_huge(*pmd))) { @@ -2495,6 +2500,16 @@ void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd) BUG_ON(pmd_trans_huge(*pmd)); } +void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, + pmd_t *pmd) +{ + struct vm_area_struct *vma; + + vma = find_vma(mm, address); + BUG_ON(vma == NULL); + split_huge_page_pmd(vma, address, pmd); +} + static void split_huge_page_address(struct mm_struct *mm, unsigned long address) { @@ -2509,7 +2524,7 @@ static void split_huge_page_address(struct mm_struct *mm, * Caller holds the mmap_sem write mode, so a huge pmd cannot * materialize from under us. */ - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd_mm(mm, address, pmd); } void __vma_adjust_trans_huge(struct vm_area_struct *vma, diff --git a/mm/memory.c b/mm/memory.c index 259b34fe1347..f9a4b0cb8623 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1243,7 +1243,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, BUG(); } #endif - split_huge_page_pmd(vma->vm_mm, pmd); + split_huge_page_pmd(vma, addr, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ @@ -1512,7 +1512,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, } if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd(vma, address, pmd); goto split_fallthrough; } spin_lock(&mm->page_table_lock); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 05b28361a39b..0719e8dd4945 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -511,7 +511,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - split_huge_page_pmd(vma->vm_mm, pmd); + split_huge_page_pmd(vma, addr, pmd); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; if (check_pte_range(vma, pmd, addr, next, nodes, diff --git a/mm/mprotect.c b/mm/mprotect.c index a40992610ab6..e8c3938db6fa 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -90,7 +90,7 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) - split_huge_page_pmd(vma->vm_mm, pmd); + split_huge_page_pmd(vma, addr, pmd); else if (change_huge_pmd(vma, pmd, addr, newprot)) continue; /* fall through */ diff --git a/mm/mremap.c b/mm/mremap.c index 1b61c2d3307a..eabb24da6c9e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -182,7 +182,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, need_flush = true; continue; } else if (!err) { - split_huge_page_pmd(vma->vm_mm, old_pmd); + split_huge_page_pmd(vma, old_addr, old_pmd); } VM_BUG_ON(pmd_trans_huge(*old_pmd)); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 6c118d012bb5..35aa294656cd 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -58,7 +58,7 @@ again: if (!walk->pte_entry) continue; - split_huge_page_pmd(walk->mm, pmd); + split_huge_page_pmd_mm(walk->mm, addr, pmd); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); -- cgit v1.2.3 From 11520e5e7c1855fc3bf202bb3be35a39d9efa034 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 15 Dec 2012 15:15:24 -0800 Subject: Revert "x86-64/efi: Use EFI to deal with platform wall clock (again)" This reverts commit bd52276fa1d4 ("x86-64/efi: Use EFI to deal with platform wall clock (again)"), and the two supporting commits: da5a108d05b4: "x86/kernel: remove tboot 1:1 page table creation code" 185034e72d59: "x86, efi: 1:1 pagetable mapping for virtual EFI calls") as they all depend semantically on commit 53b87cf088e2 ("x86, mm: Include the entire kernel memory map in trampoline_pgd") that got reverted earlier due to the problems it caused. This was pointed out by Yinghai Lu, and verified by me on my Macbook Air that uses EFI. Pointed-out-by: Yinghai Lu Signed-off-by: Linus Torvalds --- arch/x86/include/asm/efi.h | 28 ++++----------- arch/x86/kernel/tboot.c | 78 +++++++++++++++++++++++++++++++++++++++--- arch/x86/mm/pageattr.c | 10 +++--- arch/x86/platform/efi/efi.c | 30 +++++++++++++--- arch/x86/platform/efi/efi_64.c | 15 -------- include/linux/efi.h | 2 ++ init/main.c | 8 ++--- 7 files changed, 116 insertions(+), 55 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index fd13815fe85c..6e8fdf5ad113 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -69,37 +69,23 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3), \ (u64)(a4), (u64)(a5), (u64)(a6)) -extern unsigned long efi_call_virt_prelog(void); -extern void efi_call_virt_epilog(unsigned long); - -#define efi_callx(x, func, ...) \ - ({ \ - efi_status_t __status; \ - unsigned long __pgd; \ - \ - __pgd = efi_call_virt_prelog(); \ - __status = efi_call##x(func, __VA_ARGS__); \ - efi_call_virt_epilog(__pgd); \ - __status; \ - }) - #define efi_call_virt0(f) \ - efi_callx(0, (void *)(efi.systab->runtime->f)) + efi_call0((void *)(efi.systab->runtime->f)) #define efi_call_virt1(f, a1) \ - efi_callx(1, (void *)(efi.systab->runtime->f), (u64)(a1)) + efi_call1((void *)(efi.systab->runtime->f), (u64)(a1)) #define efi_call_virt2(f, a1, a2) \ - efi_callx(2, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2)) + efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2)) #define efi_call_virt3(f, a1, a2, a3) \ - efi_callx(3, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3)) #define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_callx(4, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4)) #define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - efi_callx(5, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5)) #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - efi_callx(6, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index d4f460f962ee..f84fe00fad48 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -103,13 +103,71 @@ void __init tboot_probe(void) pr_debug("tboot_size: 0x%x\n", tboot->tboot_size); } +static pgd_t *tboot_pg_dir; +static struct mm_struct tboot_mm = { + .mm_rb = RB_ROOT, + .pgd = swapper_pg_dir, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), + .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), + .mmlist = LIST_HEAD_INIT(init_mm.mmlist), +}; + static inline void switch_to_tboot_pt(void) { -#ifdef CONFIG_X86_32 - load_cr3(initial_page_table); -#else - write_cr3(real_mode_header->trampoline_pgd); -#endif + write_cr3(virt_to_phys(tboot_pg_dir)); +} + +static int map_tboot_page(unsigned long vaddr, unsigned long pfn, + pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset(&tboot_mm, vaddr); + pud = pud_alloc(&tboot_mm, pgd, vaddr); + if (!pud) + return -1; + pmd = pmd_alloc(&tboot_mm, pud, vaddr); + if (!pmd) + return -1; + pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr); + if (!pte) + return -1; + set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); + pte_unmap(pte); + return 0; +} + +static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn, + unsigned long nr) +{ + /* Reuse the original kernel mapping */ + tboot_pg_dir = pgd_alloc(&tboot_mm); + if (!tboot_pg_dir) + return -1; + + for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) { + if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC)) + return -1; + } + + return 0; +} + +static void tboot_create_trampoline(void) +{ + u32 map_base, map_size; + + /* Create identity map for tboot shutdown code. */ + map_base = PFN_DOWN(tboot->tboot_base); + map_size = PFN_UP(tboot->tboot_size); + if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size)) + panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n", + map_base, map_size); } #ifdef CONFIG_ACPI_SLEEP @@ -167,6 +225,14 @@ void tboot_shutdown(u32 shutdown_type) if (!tboot_enabled()) return; + /* + * if we're being called before the 1:1 mapping is set up then just + * return and let the normal shutdown happen; this should only be + * due to very early panic() + */ + if (!tboot_pg_dir) + return; + /* if this is S3 then set regions to MAC */ if (shutdown_type == TB_SHUTDOWN_S3) if (tboot_setup_sleep()) @@ -277,6 +343,8 @@ static __init int tboot_late_init(void) if (!tboot_enabled()) return 0; + tboot_create_trampoline(); + atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 931930a96160..a718e0d23503 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it, in the - * error case, and during early boot (for EFI) we fall back - * to cpa_flush_all (which uses wbinvd): + * avoid the wbindv. If the CPU does not support it and in the + * error case we fall back to cpa_flush_all (which uses + * wbindv): */ - if (early_boot_irqs_disabled) - __cpa_flush_all((void *)(long)cache); - else if (!ret && cpu_has_clflush) { + if (!ret && cpu_has_clflush) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 0a34d9e9c263..ad4439145f85 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -239,7 +239,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -static int efi_set_rtc_mmss(unsigned long nowtime) +static efi_status_t __init phys_efi_get_time(efi_time_t *tm, + efi_time_cap_t *tc) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + efi_call_phys_prelog(); + status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm), + virt_to_phys(tc)); + efi_call_phys_epilog(); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +int efi_set_rtc_mmss(unsigned long nowtime) { int real_seconds, real_minutes; efi_status_t status; @@ -268,7 +283,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -static unsigned long efi_get_time(void) +unsigned long efi_get_time(void) { efi_status_t status; efi_time_t eft; @@ -624,13 +639,18 @@ static int __init efi_runtime_init(void) } /* * We will only need *early* access to the following - * EFI runtime service before set_virtual_address_map + * two EFI runtime services before set_virtual_address_map * is invoked. */ + efi_phys.get_time = (efi_get_time_t *)runtime->get_time; efi_phys.set_virtual_address_map = (efi_set_virtual_address_map_t *) runtime->set_virtual_address_map; - + /* + * Make efi_get_time can be called before entering + * virtual mode. + */ + efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); return 0; @@ -716,10 +736,12 @@ void __init efi_init(void) efi_enabled = 0; return; } +#ifdef CONFIG_X86_32 if (efi_is_native()) { x86_platform.get_wallclock = efi_get_time; x86_platform.set_wallclock = efi_set_rtc_mmss; } +#endif #if EFI_DEBUG print_efi_memmap(); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 06c8b2e662ab..95fd505dfeb6 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -58,21 +58,6 @@ static void __init early_code_mapping_set_exec(int executable) } } -unsigned long efi_call_virt_prelog(void) -{ - unsigned long saved; - - saved = read_cr3(); - write_cr3(real_mode_header->trampoline_pgd); - - return saved; -} - -void efi_call_virt_epilog(unsigned long saved) -{ - write_cr3(saved); -} - void __init efi_call_phys_prelog(void) { unsigned long vaddress; diff --git a/include/linux/efi.h b/include/linux/efi.h index 02a69418be18..8b84916dc671 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -587,6 +587,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); +extern unsigned long efi_get_time(void); +extern int efi_set_rtc_mmss(unsigned long nowtime); extern void efi_reserve_boot_services(void); extern struct efi_memory_map memmap; diff --git a/init/main.c b/init/main.c index 6af5470b8067..63ae904a99a8 100644 --- a/init/main.c +++ b/init/main.c @@ -463,10 +463,6 @@ static void __init mm_init(void) percpu_init_late(); pgtable_cache_init(); vmalloc_init(); -#ifdef CONFIG_X86 - if (efi_enabled) - efi_enter_virtual_mode(); -#endif } asmlinkage void __init start_kernel(void) @@ -607,6 +603,10 @@ asmlinkage void __init start_kernel(void) calibrate_delay(); pidmap_init(); anon_vma_init(); +#ifdef CONFIG_X86 + if (efi_enabled) + efi_enter_virtual_mode(); +#endif thread_info_cache_init(); cred_init(); fork_init(totalram_pages); -- cgit v1.2.3 From bc3eba60682750dd7b45ea616d65c926fc3b8be8 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 17 Dec 2012 11:26:31 -0800 Subject: x86, 386 removal: Remove support for IRQ 13 FPU error reporting Remove support for FPU error reporting via IRQ 13, as opposed to exception 16 (#MF). One last remnant of i386 gone. Signed-off-by: H. Peter Anvin Cc: Alan Cox --- arch/x86/kernel/cpu/proc.c | 7 +------ arch/x86/kernel/irqinit.c | 40 ---------------------------------------- arch/x86/kernel/traps.c | 6 ------ 3 files changed, 1 insertion(+), 52 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index fbd895562292..3286a92e662a 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -26,11 +26,6 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, #ifdef CONFIG_X86_32 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { - /* - * We use exception 16 if we have hardware math and we've either seen - * it or the CPU claims it is internal - */ - int fpu_exception = c->hard_math && (ignore_fpu_irq || cpu_has_fpu); seq_printf(m, "fdiv_bug\t: %s\n" "hlt_bug\t\t: %s\n" @@ -45,7 +40,7 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) c->f00f_bug ? "yes" : "no", c->coma_bug ? "yes" : "no", c->hard_math ? "yes" : "no", - fpu_exception ? "yes" : "no", + c->hard_math ? "yes" : "no", c->cpuid_level, c->wp_works_ok ? "yes" : "no"); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 6e03b0d69138..7dc4e459c2b3 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -42,39 +42,6 @@ * (these are usually mapped into the 0x30-0xff vector range) */ -#ifdef CONFIG_X86_32 -/* - * Note that on a 486, we don't want to do a SIGFPE on an irq13 - * as the irq is unreliable, and exception 16 works correctly - * (ie as explained in the intel literature). On a 386, you - * can't use exception 16 due to bad IBM design, so we have to - * rely on the less exact irq13. - * - * Careful.. Not only is IRQ13 unreliable, but it is also - * leads to races. IBM designers who came up with it should - * be shot. - */ - -static irqreturn_t math_error_irq(int cpl, void *dev_id) -{ - outb(0, 0xF0); - if (ignore_fpu_irq || !boot_cpu_data.hard_math) - return IRQ_NONE; - math_error(get_irq_regs(), 0, X86_TRAP_MF); - return IRQ_HANDLED; -} - -/* - * New motherboards sometimes make IRQ 13 be a PCI interrupt, - * so allow interrupt sharing. - */ -static struct irqaction fpu_irq = { - .handler = math_error_irq, - .name = "fpu", - .flags = IRQF_NO_THREAD, -}; -#endif - /* * IRQ2 is cascade interrupt to second interrupt controller */ @@ -242,13 +209,6 @@ void __init native_init_IRQ(void) setup_irq(2, &irq2); #ifdef CONFIG_X86_32 - /* - * External FPU? Set up irq13 if so, for - * original braindamaged IBM FERR coupling. - */ - if (boot_cpu_data.hard_math && !cpu_has_fpu) - setup_irq(FPU_IRQ, &fpu_irq); - irq_ctx_init(smp_processor_id()); #endif } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8276dc6794cc..4e1478c12344 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -69,9 +69,6 @@ asmlinkage int system_call(void); -/* Do we ignore FPU interrupts ? */ -char ignore_fpu_irq; - /* * The IDT has to be page-aligned to simplify the Pentium * F0 0F bug workaround. @@ -564,9 +561,6 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_X86_32 - ignore_fpu_irq = 1; -#endif exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); exception_exit(regs); -- cgit v1.2.3 From 9b132fbe5419d789f1ef396bed5eb66a365dd1e9 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Tue, 4 Dec 2012 10:35:13 +0800 Subject: Add rcu user eqs exception hooks for async page fault This patch adds user eqs exception hooks for async page fault page not present code path, to exit the user eqs and re-enter it as necessary. Async page fault is different from other exceptions that it may be triggered from idle process, so we still need rcu_irq_enter() and rcu_irq_exit() to exit cpu idle eqs when needed, to protect the code that needs use rcu. As Frederic pointed out it would be safest and simplest to protect the whole kvm_async_pf_task_wait(). Otherwise, "we need to check all the code there deeply for potential RCU uses and ensure it will never be extended later to use RCU.". However, We'd better re-enter the cpu idle eqs if we get the exception in cpu idle eqs, by calling rcu_irq_exit() before native_safe_halt(). So the patch does what Frederic suggested for rcu_irq_*() API usage here, except that I moved the rcu_irq_*() pair originally in do_async_page_fault() into kvm_async_pf_task_wait(). That's because, I think it's better to have rcu_irq_*() pairs to be in one function ( rcu_irq_exit() after rcu_irq_enter() ), especially here, kvm_async_pf_task_wait() has other callers, which might cause rcu_irq_exit() be called without a matching rcu_irq_enter() before it, which is illegal if the cpu happens to be in rcu idle state. Signed-off-by: Li Zhong Signed-off-by: Gleb Natapov --- arch/x86/kernel/kvm.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 08b973f64032..9c2bd8bd4b4c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -43,6 +43,7 @@ #include #include #include +#include static int kvmapf = 1; @@ -121,6 +122,8 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); + rcu_irq_enter(); + spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { @@ -128,6 +131,8 @@ void kvm_async_pf_task_wait(u32 token) hlist_del(&e->link); kfree(e); spin_unlock(&b->lock); + + rcu_irq_exit(); return; } @@ -152,13 +157,16 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ + rcu_irq_exit(); native_safe_halt(); + rcu_irq_enter(); local_irq_disable(); } } if (!n.halted) finish_wait(&n.wq, &wait); + rcu_irq_exit(); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); @@ -252,10 +260,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - rcu_irq_enter(); + exception_enter(regs); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - rcu_irq_exit(); + exception_exit(regs); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); -- cgit v1.2.3 From 6bf9adfc90370b695cb111116e15fdc0e1906270 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 14 Dec 2012 14:09:47 -0500 Subject: introduce generic sys_sigaltstack(), switch x86 and um to it Conditional on CONFIG_GENERIC_SIGALTSTACK; architectures that do not select it are completely unaffected Signed-off-by: Al Viro --- arch/Kconfig | 3 +++ arch/um/kernel/signal.c | 5 ----- arch/x86/Kconfig | 1 + arch/x86/include/asm/syscalls.h | 3 --- arch/x86/kernel/entry_32.S | 1 - arch/x86/kernel/entry_64.S | 1 - arch/x86/kernel/signal.c | 7 ------- arch/x86/syscalls/syscall_32.tbl | 2 +- arch/x86/syscalls/syscall_64.tbl | 2 +- arch/x86/um/Kconfig | 1 + arch/x86/um/sys_call_table_32.c | 1 - arch/x86/um/sys_call_table_64.c | 1 - include/linux/syscalls.h | 6 ++++++ kernel/signal.c | 6 ++++++ 14 files changed, 19 insertions(+), 21 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/Kconfig b/arch/Kconfig index 0a8dd0585d0d..330176824594 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -335,6 +335,9 @@ config MODULES_USE_ELF_REL Modules only use ELF REL relocations. Modules with ELF RELA relocations will give an error. +config GENERIC_SIGALTSTACK + bool + # # ABI hall of shame # diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index db18eb6124e1..48ccf718e290 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -132,8 +132,3 @@ long sys_sigsuspend(int history0, int history1, old_sigset_t mask) siginitset(&blocked, mask); return sigsuspend(&blocked); } - -long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss) -{ - return do_sigaltstack(uss, uoss, PT_REGS_SP(¤t->thread.regs)); -} diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 01ca0ebaff0e..f380614d7d89 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -111,6 +111,7 @@ config X86 select MODULES_USE_ELF_REL if X86_32 select MODULES_USE_ELF_RELA if X86_64 select CLONE_BACKWARDS if X86_32 + select GENERIC_SIGALTSTACK config INSTRUCTION_DECODER def_bool y diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 2f8374718aa3..58b7e3eac0ae 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -25,9 +25,6 @@ asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ long sys_rt_sigreturn(struct pt_regs *); -long sys_sigaltstack(const stack_t __user *, stack_t __user *, - struct pt_regs *); - /* kernel/tls.c */ asmlinkage int sys_set_thread_area(struct user_desc __user *); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c763116c5359..ff84d5469d77 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -739,7 +739,6 @@ ENTRY(ptregs_##name) ; \ ENDPROC(ptregs_##name) PTREGSCALL1(iopl) -PTREGSCALL2(sigaltstack) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2363e820ed68..6e462019f195 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -864,7 +864,6 @@ END(stub_\func) FORK_LIKE clone FORK_LIKE fork FORK_LIKE vfork - PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx PTREGSCALL stub_iopl, sys_iopl, %rsi ENTRY(ptregscall_common) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 70b27ee6118e..16d065c23baf 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -602,13 +602,6 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #endif /* CONFIG_X86_32 */ -long -sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, - struct pt_regs *regs) -{ - return do_sigaltstack(uss, uoss, regs->sp); -} - /* * Do a signal return; undo the signal stack. */ diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index ee3c220ee500..62c7b222e45c 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -192,7 +192,7 @@ 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget 185 i386 capset sys_capset -186 i386 sigaltstack ptregs_sigaltstack stub32_sigaltstack +186 i386 sigaltstack sys_sigaltstack stub32_sigaltstack 187 i386 sendfile sys_sendfile sys32_sendfile 188 i386 getpmsg 189 i386 putpmsg diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index a582bfed95bb..6ffa7f9d005e 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -137,7 +137,7 @@ 128 64 rt_sigtimedwait sys_rt_sigtimedwait 129 64 rt_sigqueueinfo sys_rt_sigqueueinfo 130 common rt_sigsuspend sys_rt_sigsuspend -131 64 sigaltstack stub_sigaltstack +131 64 sigaltstack sys_sigaltstack 132 common utime sys_utime 133 common mknod sys_mknod 134 64 uselib diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 0fd20f241e40..96b89d874ead 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -13,6 +13,7 @@ endmenu config UML_X86 def_bool y select GENERIC_FIND_FIRST_BIT + select GENERIC_SIGALTSTACK config 64BIT bool "64-bit kernel" if SUBARCH = "x86" diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 812e98c098e4..a0c3b0d1a122 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -27,7 +27,6 @@ #define ptregs_iopl sys_iopl #define ptregs_vm86old sys_vm86old #define ptregs_vm86 sys_vm86 -#define ptregs_sigaltstack sys_sigaltstack #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; #include diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 170bd926a69c..f2f0723070ca 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -31,7 +31,6 @@ #define stub_fork sys_fork #define stub_vfork sys_vfork #define stub_execve sys_execve -#define stub_sigaltstack sys_sigaltstack #define stub_rt_sigreturn sys_rt_sigreturn #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 9fe5f946526e..6ca1e08210c6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -63,6 +63,7 @@ struct getcpu_cache; struct old_linux_dirent; struct perf_event_attr; struct file_handle; +struct sigaltstack; #include #include @@ -299,6 +300,11 @@ asmlinkage long sys_personality(unsigned int personality); asmlinkage long sys_sigpending(old_sigset_t __user *set); asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset); +#ifdef CONFIG_GENERIC_SIGALTSTACK +asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, + struct sigaltstack __user *uoss); +#endif + asmlinkage long sys_getitimer(int which, struct itimerval __user *value); asmlinkage long sys_setitimer(int which, struct itimerval __user *value, diff --git a/kernel/signal.c b/kernel/signal.c index 887f2fefe207..f05f4c4150d9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3102,6 +3102,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s out: return error; } +#ifdef CONFIG_GENERIC_SIGALTSTACK +SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) +{ + return do_sigaltstack(uss, uoss, current_user_stack_pointer()); +} +#endif int restore_altstack(const stack_t __user *uss) { -- cgit v1.2.3 From 9026843952adac5b123c7b8dc961e5c15828d9e1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 14 Dec 2012 14:47:53 -0500 Subject: generic compat_sys_sigaltstack() Again, conditional on CONFIG_GENERIC_SIGALTSTACK Signed-off-by: Al Viro --- arch/x86/ia32/ia32_signal.c | 50 +--------------------------------------- arch/x86/ia32/ia32entry.S | 1 - arch/x86/include/asm/ia32.h | 10 ++------ arch/x86/include/asm/sys_ia32.h | 2 -- arch/x86/kernel/entry_64.S | 2 -- arch/x86/kernel/signal.c | 4 +--- arch/x86/syscalls/syscall_32.tbl | 2 +- arch/x86/syscalls/syscall_64.tbl | 2 +- include/linux/compat.h | 16 +++++++++++++ kernel/signal.c | 45 ++++++++++++++++++++++++++++++++++++ 10 files changed, 67 insertions(+), 67 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index efc6a958b71d..a866411a2fcc 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -136,52 +136,6 @@ asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask) return sigsuspend(&blocked); } -asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, - stack_ia32_t __user *uoss_ptr, - struct pt_regs *regs) -{ - stack_t uss, uoss; - int ret, err = 0; - mm_segment_t seg; - - if (uss_ptr) { - u32 ptr; - - memset(&uss, 0, sizeof(stack_t)); - if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t))) - return -EFAULT; - - get_user_try { - get_user_ex(ptr, &uss_ptr->ss_sp); - get_user_ex(uss.ss_flags, &uss_ptr->ss_flags); - get_user_ex(uss.ss_size, &uss_ptr->ss_size); - } get_user_catch(err); - - if (err) - return -EFAULT; - uss.ss_sp = compat_ptr(ptr); - } - seg = get_fs(); - set_fs(KERNEL_DS); - ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), - (stack_t __force __user *) &uoss, regs->sp); - set_fs(seg); - if (ret >= 0 && uoss_ptr) { - if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t))) - return -EFAULT; - - put_user_try { - put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp); - put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags); - put_user_ex(uoss.ss_size, &uoss_ptr->ss_size); - } put_user_catch(err); - - if (err) - ret = -EFAULT; - } - return ret; -} - /* * Do a signal return; undo the signal stack. */ @@ -292,7 +246,6 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs) struct rt_sigframe_ia32 __user *frame; sigset_t set; unsigned int ax; - struct pt_regs tregs; frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4); @@ -306,8 +259,7 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs) if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - tregs = *regs; - if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 32e6f05ddaaa..102ff7cb3e41 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -464,7 +464,6 @@ GLOBAL(\label) PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi - PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx PTREGSCALL stub32_execve, compat_sys_execve, %rcx PTREGSCALL stub32_fork, sys_fork, %rdi PTREGSCALL stub32_vfork, sys_vfork, %rdi diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index e6232773ce49..4c6da2e4bb1d 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -29,16 +29,10 @@ struct old_sigaction32 { unsigned int sa_restorer; /* Another 32 bit pointer */ }; -typedef struct sigaltstack_ia32 { - unsigned int ss_sp; - int ss_flags; - unsigned int ss_size; -} stack_ia32_t; - struct ucontext_ia32 { unsigned int uc_flags; unsigned int uc_link; - stack_ia32_t uc_stack; + compat_stack_t uc_stack; struct sigcontext_ia32 uc_mcontext; compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; @@ -46,7 +40,7 @@ struct ucontext_ia32 { struct ucontext_x32 { unsigned int uc_flags; unsigned int uc_link; - stack_ia32_t uc_stack; + compat_stack_t uc_stack; unsigned int uc__pad0; /* needed for alignment */ struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ compat_sigset_t uc_sigmask; /* mask last for extensibility */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index c76fae4d90be..31f61f96e0fb 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -69,8 +69,6 @@ asmlinkage long sys32_fallocate(int, int, unsigned, /* ia32/ia32_signal.c */ asmlinkage long sys32_sigsuspend(int, int, old_sigset_t); -asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *, - stack_ia32_t __user *, struct pt_regs *); asmlinkage long sys32_sigreturn(struct pt_regs *); asmlinkage long sys32_rt_sigreturn(struct pt_regs *); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 6e462019f195..86d81199bbde 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -912,8 +912,6 @@ ENTRY(stub_rt_sigreturn) END(stub_rt_sigreturn) #ifdef CONFIG_X86_X32_ABI - PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx - ENTRY(stub_x32_rt_sigreturn) CFI_STARTPROC addq $8, %rsp diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 16d065c23baf..b17ed37c61a2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -857,7 +857,6 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) struct rt_sigframe_x32 __user *frame; sigset_t set; unsigned long ax; - struct pt_regs tregs; frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); @@ -871,8 +870,7 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - tregs = *regs; - if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index 62c7b222e45c..235226efaa7f 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -192,7 +192,7 @@ 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget 185 i386 capset sys_capset -186 i386 sigaltstack sys_sigaltstack stub32_sigaltstack +186 i386 sigaltstack sys_sigaltstack compat_sys_sigaltstack 187 i386 sendfile sys_sendfile sys32_sendfile 188 i386 getpmsg 189 i386 putpmsg diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 6ffa7f9d005e..c68cbe7174e7 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -337,7 +337,7 @@ 522 x32 rt_sigpending sys32_rt_sigpending 523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait 524 x32 rt_sigqueueinfo sys32_rt_sigqueueinfo -525 x32 sigaltstack stub_x32_sigaltstack +525 x32 sigaltstack compat_sys_sigaltstack 526 x32 timer_create compat_sys_timer_create 527 x32 mq_notify compat_sys_mq_notify 528 x32 kexec_load compat_sys_kexec_load diff --git a/include/linux/compat.h b/include/linux/compat.h index 62bb76f91baf..cb5637e2ee2c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -68,6 +68,16 @@ #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif +#ifdef CONFIG_GENERIC_SIGALTSTACK +#ifndef compat_sigaltstack /* we'll need that for MIPS */ +typedef struct compat_sigaltstack { + compat_uptr_t ss_sp; + int ss_flags; + compat_size_t ss_size; +} compat_stack_t; +#endif +#endif + #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) @@ -632,6 +642,12 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); +#ifdef CONFIG_GENERIC_SIGALTSTACK +asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, + compat_stack_t __user *uoss_ptr); + +int compat_restore_altstack(const compat_stack_t __user *uss); +#endif #else diff --git a/kernel/signal.c b/kernel/signal.c index f05f4c4150d9..aee85bd76b8a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -31,6 +31,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -3116,6 +3117,50 @@ int restore_altstack(const stack_t __user *uss) return err == -EFAULT ? err : 0; } +#ifdef CONFIG_COMPAT +#ifdef CONFIG_GENERIC_SIGALTSTACK +asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, + compat_stack_t __user *uoss_ptr) +{ + stack_t uss, uoss; + int ret; + mm_segment_t seg; + + if (uss_ptr) { + compat_stack_t uss32; + + memset(&uss, 0, sizeof(stack_t)); + if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) + return -EFAULT; + uss.ss_sp = compat_ptr(uss32.ss_sp); + uss.ss_flags = uss32.ss_flags; + uss.ss_size = uss32.ss_size; + } + seg = get_fs(); + set_fs(KERNEL_DS); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, + compat_user_stack_pointer()); + set_fs(seg); + if (ret >= 0 && uoss_ptr) { + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) || + __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || + __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || + __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + ret = -EFAULT; + } + return ret; +} + +int compat_restore_altstack(const compat_stack_t __user *uss) +{ + int err = compat_sys_sigaltstack(uss, NULL); + /* squash all but -EFAULT for now */ + return err == -EFAULT ? err : 0; +} +#endif +#endif + #ifdef __ARCH_WANT_SYS_SIGPENDING /** -- cgit v1.2.3 From c40702c49faef05ae324f121d8b3e215244ee152 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 20 Nov 2012 14:24:26 -0500 Subject: new helpers: __save_altstack/__compat_save_altstack, switch x86 and um to those note that they are relying on access_ok() already checked by caller. Signed-off-by: Al Viro --- arch/x86/ia32/ia32_signal.c | 5 +---- arch/x86/kernel/signal.c | 18 ++++-------------- arch/x86/um/signal.c | 9 ++------- include/linux/compat.h | 1 + include/linux/signal.h | 1 + kernel/signal.c | 16 ++++++++++++++++ 6 files changed, 25 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index a866411a2fcc..a1daf4a65009 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -467,10 +467,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); if (ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b17ed37c61a2..a6c8a347b8c6 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -363,10 +363,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -413,7 +410,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct rt_sigframe __user *frame; void __user *fp = NULL; int err = 0; - struct task_struct *me = current; frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp); @@ -432,10 +428,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -502,10 +495,7 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ka->sa.sa_flags & SA_RESTORER) { @@ -651,7 +641,7 @@ long sys_rt_sigreturn(struct pt_regs *regs) if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index bdaa08cfbcf4..71cef48ea5cd 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -342,9 +342,7 @@ static int copy_ucontext_to_user(struct ucontext __user *uc, { int err = 0; - err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp); - err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags); - err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size); + err |= __save_altstack(&uc->uc_stack, sp); err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs, 0); err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set)); return err; @@ -529,10 +527,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); diff --git a/include/linux/compat.h b/include/linux/compat.h index cb5637e2ee2c..334813307ec1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -647,6 +647,7 @@ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); int compat_restore_altstack(const compat_stack_t __user *uss); +int __compat_save_altstack(compat_stack_t __user *, unsigned long); #endif #else diff --git a/include/linux/signal.h b/include/linux/signal.h index 5969522136fe..0a89ffc48466 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -386,5 +386,6 @@ int unhandled_signal(struct task_struct *tsk, int sig); void signals_init(void); int restore_altstack(const stack_t __user *); +int __save_altstack(stack_t __user *, unsigned long); #endif /* _LINUX_SIGNAL_H */ diff --git a/kernel/signal.c b/kernel/signal.c index aee85bd76b8a..f072513302c3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3117,6 +3117,14 @@ int restore_altstack(const stack_t __user *uss) return err == -EFAULT ? err : 0; } +int __save_altstack(stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} + #ifdef CONFIG_COMPAT #ifdef CONFIG_GENERIC_SIGALTSTACK asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, @@ -3158,6 +3166,14 @@ int compat_restore_altstack(const compat_stack_t __user *uss) /* squash all but -EFAULT for now */ return err == -EFAULT ? err : 0; } + +int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} #endif #endif -- cgit v1.2.3 From a18e3690a52790a034d6540d54e8e1f1cd125da2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 21 Dec 2012 14:02:53 -0800 Subject: X86: drivers: remove __dev* attributes. CONFIG_HOTPLUG is going away as an option. As a result, the __dev* markings need to be removed. This change removes the use of __devinit, __devexit_p, __devinitconst, and __devexit from these drivers. Based on patches originally written by Bill Pemberton, but redone by me in order to handle some of the coding style issues better, by hand. Cc: Bill Pemberton Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Daniel Drake Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/parport.h | 4 ++-- arch/x86/include/asm/pci_x86.h | 7 +++---- arch/x86/kernel/cpu/perf_event_intel_uncore.c | 6 +++--- arch/x86/kernel/pci-dma.c | 2 +- arch/x86/kernel/quirks.c | 4 ++-- arch/x86/lib/delay.c | 2 +- arch/x86/pci/acpi.c | 11 +++++----- arch/x86/pci/bus_numa.c | 4 ++-- arch/x86/pci/common.c | 26 +++++++++++------------ arch/x86/pci/fixup.c | 30 +++++++++++++-------------- arch/x86/pci/legacy.c | 4 ++-- arch/x86/pci/mmconfig-shared.c | 21 ++++++++----------- arch/x86/pci/mmconfig_32.c | 2 +- arch/x86/pci/mmconfig_64.c | 4 ++-- arch/x86/pci/mrst.c | 6 +++--- arch/x86/pci/numaq_32.c | 2 +- arch/x86/pci/pcbios.c | 4 ++-- arch/x86/platform/mrst/mrst.c | 2 +- arch/x86/platform/olpc/olpc-xo1-pm.c | 8 +++---- arch/x86/platform/olpc/olpc-xo1-sci.c | 18 ++++++++-------- arch/x86/platform/scx200/scx200_32.c | 6 +++--- 21 files changed, 84 insertions(+), 89 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/parport.h b/arch/x86/include/asm/parport.h index 3c4ffeb467e9..0d2d3b29118f 100644 --- a/arch/x86/include/asm/parport.h +++ b/arch/x86/include/asm/parport.h @@ -1,8 +1,8 @@ #ifndef _ASM_X86_PARPORT_H #define _ASM_X86_PARPORT_H -static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma); -static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma) +static int parport_pc_find_isa_ports(int autoirq, int autodma); +static int parport_pc_find_nonpci_ports(int autoirq, int autodma) { return parport_pc_find_isa_ports(autoirq, autodma); } diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 73e8eeff22ee..747e5a38b590 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -140,11 +140,10 @@ struct pci_mmcfg_region { extern int __init pci_mmcfg_arch_init(void); extern void __init pci_mmcfg_arch_free(void); -extern int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg); +extern int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg); extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg); -extern int __devinit pci_mmconfig_insert(struct device *dev, - u16 seg, u8 start, - u8 end, phys_addr_t addr); +extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, + phys_addr_t addr); extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end); extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 3cf3d97cce3a..b43200dbfe7e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2500,7 +2500,7 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) +static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; @@ -2571,8 +2571,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) kfree(box); } -static int __devinit uncore_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) +static int uncore_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) { struct intel_uncore_type *type; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index de2b7ad70273..0f5dec5c80e0 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -265,7 +265,7 @@ rootfs_initcall(pci_iommu_init); #ifdef CONFIG_PCI /* Many VIA bridges seem to corrupt data for DAC. Disable it here */ -static __devinit void via_no_dac(struct pci_dev *dev) +static void via_no_dac(struct pci_dev *dev) { if (forbid_dac == 0) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 1b27de563561..26ee48a33dc4 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -8,7 +8,7 @@ #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) -static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) +static void quirk_intel_irqbalance(struct pci_dev *dev) { u8 config; u16 word; @@ -512,7 +512,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, #if defined(CONFIG_PCI) && defined(CONFIG_NUMA) /* Set correct numa_node information for AMD NB functions */ -static void __devinit quirk_amd_nb_node(struct pci_dev *dev) +static void quirk_amd_nb_node(struct pci_dev *dev) { struct pci_dev *nb_ht; unsigned int devfn; diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index e395693abdb1..7c3bee636e2f 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -98,7 +98,7 @@ void use_tsc_delay(void) delay_fn = delay_tsc; } -int __devinit read_current_timer(unsigned long *timer_val) +int read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { rdtscll(*timer_val); diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0c01261fe5a8..53ea60458e01 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -145,7 +145,7 @@ void __init pci_acpi_crs_quirks(void) } #ifdef CONFIG_PCI_MMCONFIG -static int __devinit check_segment(u16 seg, struct device *dev, char *estr) +static int check_segment(u16 seg, struct device *dev, char *estr) { if (seg) { dev_err(dev, @@ -168,9 +168,8 @@ static int __devinit check_segment(u16 seg, struct device *dev, char *estr) return 0; } -static int __devinit setup_mcfg_map(struct pci_root_info *info, - u16 seg, u8 start, u8 end, - phys_addr_t addr) +static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, + u8 end, phys_addr_t addr) { int result; struct device *dev = &info->bridge->dev; @@ -208,7 +207,7 @@ static void teardown_mcfg_map(struct pci_root_info *info) } } #else -static int __devinit setup_mcfg_map(struct pci_root_info *info, +static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, u8 end, phys_addr_t addr) { @@ -474,7 +473,7 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, info); } -struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) +struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { struct acpi_device *device = root->device; struct pci_root_info *info = NULL; diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index d37e2fec97e5..c2735feb2508 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -93,8 +93,8 @@ struct pci_root_info __init *alloc_pci_root_info(int bus_min, int bus_max, return info; } -void __devinit update_res(struct pci_root_info *info, resource_size_t start, - resource_size_t end, unsigned long flags, int merge) +void update_res(struct pci_root_info *info, resource_size_t start, + resource_size_t end, unsigned long flags, int merge) { struct resource *res; struct pci_root_res *root_res; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 412e1286d1fc..ccd0ab3ab899 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -81,14 +81,14 @@ struct pci_ops pci_root_ops = { */ DEFINE_RAW_SPINLOCK(pci_config_lock); -static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d) +static int can_skip_ioresource_align(const struct dmi_system_id *d) { pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident); return 0; } -static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitconst = { +static const struct dmi_system_id can_skip_pciprobe_dmi_table[] = { /* * Systems where PCI IO resource ISA alignment can be skipped * when the ISA enable bit in the bridge control is not set @@ -125,7 +125,7 @@ void __init dmi_check_skip_isa_align(void) dmi_check_system(can_skip_pciprobe_dmi_table); } -static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) +static void pcibios_fixup_device_resources(struct pci_dev *dev) { struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; struct resource *bar_r; @@ -162,7 +162,7 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) * are examined. */ -void __devinit pcibios_fixup_bus(struct pci_bus *b) +void pcibios_fixup_bus(struct pci_bus *b) { struct pci_dev *dev; @@ -176,7 +176,7 @@ void __devinit pcibios_fixup_bus(struct pci_bus *b) * on the kernel command line (which was parsed earlier). */ -static int __devinit set_bf_sort(const struct dmi_system_id *d) +static int set_bf_sort(const struct dmi_system_id *d) { if (pci_bf_sort == pci_bf_sort_default) { pci_bf_sort = pci_dmi_bf; @@ -185,7 +185,7 @@ static int __devinit set_bf_sort(const struct dmi_system_id *d) return 0; } -static void __devinit read_dmi_type_b1(const struct dmi_header *dm, +static void read_dmi_type_b1(const struct dmi_header *dm, void *private_data) { u8 *d = (u8 *)dm + 4; @@ -207,7 +207,7 @@ static void __devinit read_dmi_type_b1(const struct dmi_header *dm, } } -static int __devinit find_sort_method(const struct dmi_system_id *d) +static int find_sort_method(const struct dmi_system_id *d) { dmi_walk(read_dmi_type_b1, NULL); @@ -222,7 +222,7 @@ static int __devinit find_sort_method(const struct dmi_system_id *d) * Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus) */ #ifdef __i386__ -static int __devinit assign_all_busses(const struct dmi_system_id *d) +static int assign_all_busses(const struct dmi_system_id *d) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; printk(KERN_INFO "%s detected: enabling PCI bus# renumbering" @@ -231,7 +231,7 @@ static int __devinit assign_all_busses(const struct dmi_system_id *d) } #endif -static int __devinit set_scan_all(const struct dmi_system_id *d) +static int set_scan_all(const struct dmi_system_id *d) { printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n", d->ident); @@ -239,7 +239,7 @@ static int __devinit set_scan_all(const struct dmi_system_id *d) return 0; } -static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = { +static const struct dmi_system_id pciprobe_dmi_table[] = { #ifdef __i386__ /* * Laptops which need pci=assign-busses to see Cardbus cards @@ -446,7 +446,7 @@ void __init dmi_check_pciprobe(void) dmi_check_system(pciprobe_dmi_table); } -struct pci_bus * __devinit pcibios_scan_root(int busnum) +struct pci_bus *pcibios_scan_root(int busnum) { struct pci_bus *bus = NULL; @@ -665,7 +665,7 @@ int pci_ext_cfg_avail(void) return 0; } -struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) +struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) { LIST_HEAD(resources); struct pci_bus *bus = NULL; @@ -693,7 +693,7 @@ struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, return bus; } -struct pci_bus * __devinit pci_scan_bus_with_sysdata(int busno) +struct pci_bus *pci_scan_bus_with_sysdata(int busno) { return pci_scan_bus_on_node(busno, &pci_root_ops, -1); } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index af8a224db216..f5809fa2753e 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -9,7 +9,7 @@ #include #include -static void __devinit pci_fixup_i450nx(struct pci_dev *d) +static void pci_fixup_i450nx(struct pci_dev *d) { /* * i450NX -- Find and scan all secondary buses on all PXB's. @@ -34,7 +34,7 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82451NX, pci_fixup_i450nx); -static void __devinit pci_fixup_i450gx(struct pci_dev *d) +static void pci_fixup_i450gx(struct pci_dev *d) { /* * i450GX and i450KX -- Find and scan all secondary buses. @@ -48,7 +48,7 @@ static void __devinit pci_fixup_i450gx(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454GX, pci_fixup_i450gx); -static void __devinit pci_fixup_umc_ide(struct pci_dev *d) +static void pci_fixup_umc_ide(struct pci_dev *d) { /* * UM8886BF IDE controller sets region type bits incorrectly, @@ -62,7 +62,7 @@ static void __devinit pci_fixup_umc_ide(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8886BF, pci_fixup_umc_ide); -static void __devinit pci_fixup_ncr53c810(struct pci_dev *d) +static void pci_fixup_ncr53c810(struct pci_dev *d) { /* * NCR 53C810 returns class code 0 (at least on some systems). @@ -75,7 +75,7 @@ static void __devinit pci_fixup_ncr53c810(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, pci_fixup_ncr53c810); -static void __devinit pci_fixup_latency(struct pci_dev *d) +static void pci_fixup_latency(struct pci_dev *d) { /* * SiS 5597 and 5598 chipsets require latency timer set to @@ -87,7 +87,7 @@ static void __devinit pci_fixup_latency(struct pci_dev *d) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_5597, pci_fixup_latency); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_5598, pci_fixup_latency); -static void __devinit pci_fixup_piix4_acpi(struct pci_dev *d) +static void pci_fixup_piix4_acpi(struct pci_dev *d) { /* * PIIX4 ACPI device: hardwired IRQ9 @@ -163,7 +163,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8367_0, pci_fixup_ * system to PCI bus no matter what are their window settings, so they are * "transparent" (or subtractive decoding) from programmers point of view. */ -static void __devinit pci_fixup_transparent_bridge(struct pci_dev *dev) +static void pci_fixup_transparent_bridge(struct pci_dev *dev) { if ((dev->device & 0xff00) == 0x2400) dev->transparent = 1; @@ -317,7 +317,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC1, pcie_r * video device at this point. */ -static void __devinit pci_fixup_video(struct pci_dev *pdev) +static void pci_fixup_video(struct pci_dev *pdev) { struct pci_dev *bridge; struct pci_bus *bus; @@ -357,7 +357,7 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); -static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = { +static const struct dmi_system_id msi_k8t_dmi_table[] = { { .ident = "MSI-K8T-Neo2Fir", .matches = { @@ -378,7 +378,7 @@ static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = { * The soundcard is only enabled, if the mainborad is identified * via DMI-tables and the soundcard is detected to be off. */ -static void __devinit pci_fixup_msi_k8t_onboard_sound(struct pci_dev *dev) +static void pci_fixup_msi_k8t_onboard_sound(struct pci_dev *dev) { unsigned char val; if (!dmi_check_system(msi_k8t_dmi_table)) @@ -414,7 +414,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, */ static u16 toshiba_line_size; -static const struct dmi_system_id __devinitconst toshiba_ohci1394_dmi_table[] = { +static const struct dmi_system_id toshiba_ohci1394_dmi_table[] = { { .ident = "Toshiba PS5 based laptop", .matches = { @@ -439,7 +439,7 @@ static const struct dmi_system_id __devinitconst toshiba_ohci1394_dmi_table[] = { } }; -static void __devinit pci_pre_fixup_toshiba_ohci1394(struct pci_dev *dev) +static void pci_pre_fixup_toshiba_ohci1394(struct pci_dev *dev) { if (!dmi_check_system(toshiba_ohci1394_dmi_table)) return; /* only applies to certain Toshibas (so far) */ @@ -450,7 +450,7 @@ static void __devinit pci_pre_fixup_toshiba_ohci1394(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0x8032, pci_pre_fixup_toshiba_ohci1394); -static void __devinit pci_post_fixup_toshiba_ohci1394(struct pci_dev *dev) +static void pci_post_fixup_toshiba_ohci1394(struct pci_dev *dev) { if (!dmi_check_system(toshiba_ohci1394_dmi_table)) return; /* only applies to certain Toshibas (so far) */ @@ -488,7 +488,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, * Siemens Nixdorf AG FSC Multiprocessor Interrupt Controller: * prevent update of the BAR0, which doesn't look like a normal BAR. */ -static void __devinit pci_siemens_interrupt_controller(struct pci_dev *dev) +static void pci_siemens_interrupt_controller(struct pci_dev *dev) { dev->resource[0].flags |= IORESOURCE_PCI_FIXED; } @@ -531,7 +531,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); * * Match off the LPC and svid/sdid (older kernels lose the bridge subvendor) */ -static void __devinit twinhead_reserve_killing_zone(struct pci_dev *dev) +static void twinhead_reserve_killing_zone(struct pci_dev *dev) { if (dev->subsystem_vendor == 0x14FF && dev->subsystem_device == 0xA003) { pr_info("Reserving memory on Twinhead H12Y\n"); diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index a1df191129d3..4a2ab9cb3659 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -10,7 +10,7 @@ * Discover remaining PCI buses in case there are peer host bridges. * We use the number of last PCI bus provided by the PCI BIOS. */ -static void __devinit pcibios_fixup_peer_bridges(void) +static void pcibios_fixup_peer_bridges(void) { int n; @@ -34,7 +34,7 @@ int __init pci_legacy_init(void) return 0; } -void __devinit pcibios_scan_specific_bus(int busn) +void pcibios_scan_specific_bus(int busn) { int devfn; long node; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 704b9ec043d7..fb29968a7cd5 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -49,7 +49,7 @@ static __init void free_all_mmcfg(void) pci_mmconfig_remove(cfg); } -static __devinit void list_add_sorted(struct pci_mmcfg_region *new) +static void list_add_sorted(struct pci_mmcfg_region *new) { struct pci_mmcfg_region *cfg; @@ -65,9 +65,8 @@ static __devinit void list_add_sorted(struct pci_mmcfg_region *new) list_add_tail_rcu(&new->list, &pci_mmcfg_list); } -static __devinit struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, - int start, - int end, u64 addr) +static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start, + int end, u64 addr) { struct pci_mmcfg_region *new; struct resource *res; @@ -371,8 +370,7 @@ static int __init pci_mmcfg_check_hostbridge(void) return !list_empty(&pci_mmcfg_list); } -static acpi_status __devinit check_mcfg_resource(struct acpi_resource *res, - void *data) +static acpi_status check_mcfg_resource(struct acpi_resource *res, void *data) { struct resource *mcfg_res = data; struct acpi_resource_address64 address; @@ -408,8 +406,8 @@ static acpi_status __devinit check_mcfg_resource(struct acpi_resource *res, return AE_OK; } -static acpi_status __devinit find_mboard_resource(acpi_handle handle, u32 lvl, - void *context, void **rv) +static acpi_status find_mboard_resource(acpi_handle handle, u32 lvl, + void *context, void **rv) { struct resource *mcfg_res = context; @@ -422,7 +420,7 @@ static acpi_status __devinit find_mboard_resource(acpi_handle handle, u32 lvl, return AE_OK; } -static int __devinit is_acpi_reserved(u64 start, u64 end, unsigned not_used) +static int is_acpi_reserved(u64 start, u64 end, unsigned not_used) { struct resource mcfg_res; @@ -693,9 +691,8 @@ static int __init pci_mmcfg_late_insert_resources(void) late_initcall(pci_mmcfg_late_insert_resources); /* Add MMCFG information for host bridges */ -int __devinit pci_mmconfig_insert(struct device *dev, - u16 seg, u8 start, u8 end, - phys_addr_t addr) +int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, + phys_addr_t addr) { int rc; struct resource *tmp = NULL; diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index db63ac23e3d9..5c90975cdf0f 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -142,7 +142,7 @@ void __init pci_mmcfg_arch_free(void) { } -int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) { return 0; } diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index d4ebd07c306d..bea52496aea6 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -95,7 +95,7 @@ const struct pci_raw_ops pci_mmcfg = { .write = pci_mmcfg_write, }; -static void __iomem * __devinit mcfg_ioremap(struct pci_mmcfg_region *cfg) +static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg) { void __iomem *addr; u64 start, size; @@ -133,7 +133,7 @@ void __init pci_mmcfg_arch_free(void) pci_mmcfg_arch_unmap(cfg); } -int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) { cfg->virt = mcfg_ioremap(cfg); if (!cfg->virt) { diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index e14a2ff708b5..6eb18c42a28a 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -247,7 +247,7 @@ int __init pci_mrst_init(void) /* Langwell devices are not true pci devices, they are not subject to 10 ms * d3 to d0 delay required by pci spec. */ -static void __devinit pci_d3delay_fixup(struct pci_dev *dev) +static void pci_d3delay_fixup(struct pci_dev *dev) { /* PCI fixups are effectively decided compile time. If we have a dual SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */ @@ -262,7 +262,7 @@ static void __devinit pci_d3delay_fixup(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup); -static void __devinit mrst_power_off_unused_dev(struct pci_dev *dev) +static void mrst_power_off_unused_dev(struct pci_dev *dev) { pci_set_power_state(dev, PCI_D3hot); } @@ -275,7 +275,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0815, mrst_power_off_unused_dev); /* * Langwell devices reside at fixed offsets, don't try to move them. */ -static void __devinit pci_fixed_bar_fixup(struct pci_dev *dev) +static void pci_fixed_bar_fixup(struct pci_dev *dev) { unsigned long offset; u32 size; diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index 83e125b95ca6..b96b14c250b6 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -116,7 +116,7 @@ static const struct pci_raw_ops pci_direct_conf1_mq = { }; -static void __devinit pci_fixup_i450nx(struct pci_dev *d) +static void pci_fixup_i450nx(struct pci_dev *d) { /* * i450NX -- Find and scan all secondary buses on all PXB's. diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index da8fe0535ff4..c77b24a8b2da 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -124,7 +124,7 @@ static struct { static int pci_bios_present; -static int __devinit check_pcibios(void) +static int check_pcibios(void) { u32 signature, eax, ebx, ecx; u8 status, major_ver, minor_ver, hw_mech; @@ -312,7 +312,7 @@ static const struct pci_raw_ops pci_bios_access = { * Try to find PCI BIOS. */ -static const struct pci_raw_ops * __devinit pci_find_bios(void) +static const struct pci_raw_ops *pci_find_bios(void) { union bios32 *check; unsigned char sum; diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index fd41a9262d65..e31bcd8f2eee 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -782,7 +782,7 @@ BLOCKING_NOTIFIER_HEAD(intel_scu_notifier); EXPORT_SYMBOL_GPL(intel_scu_notifier); /* Called by IPC driver */ -void __devinit intel_scu_devices_create(void) +void intel_scu_devices_create(void) { int i; diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index d75582d1aa55..ff0174dda810 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -121,7 +121,7 @@ static const struct platform_suspend_ops xo1_suspend_ops = { .enter = xo1_power_state_enter, }; -static int __devinit xo1_pm_probe(struct platform_device *pdev) +static int xo1_pm_probe(struct platform_device *pdev) { struct resource *res; int err; @@ -154,7 +154,7 @@ static int __devinit xo1_pm_probe(struct platform_device *pdev) return 0; } -static int __devexit xo1_pm_remove(struct platform_device *pdev) +static int xo1_pm_remove(struct platform_device *pdev) { mfd_cell_disable(pdev); @@ -173,7 +173,7 @@ static struct platform_driver cs5535_pms_driver = { .owner = THIS_MODULE, }, .probe = xo1_pm_probe, - .remove = __devexit_p(xo1_pm_remove), + .remove = xo1_pm_remove, }; static struct platform_driver cs5535_acpi_driver = { @@ -182,7 +182,7 @@ static struct platform_driver cs5535_acpi_driver = { .owner = THIS_MODULE, }, .probe = xo1_pm_probe, - .remove = __devexit_p(xo1_pm_remove), + .remove = xo1_pm_remove, }; static int __init xo1_pm_init(void) diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index 63d4aa40956e..74704be7b1fe 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -309,7 +309,7 @@ static int xo1_sci_resume(struct platform_device *pdev) return 0; } -static int __devinit setup_sci_interrupt(struct platform_device *pdev) +static int setup_sci_interrupt(struct platform_device *pdev) { u32 lo, hi; u32 sts; @@ -351,7 +351,7 @@ static int __devinit setup_sci_interrupt(struct platform_device *pdev) return r; } -static int __devinit setup_ec_sci(void) +static int setup_ec_sci(void) { int r; @@ -395,7 +395,7 @@ static void free_ec_sci(void) gpio_free(OLPC_GPIO_ECSCI); } -static int __devinit setup_lid_events(void) +static int setup_lid_events(void) { int r; @@ -432,7 +432,7 @@ static void free_lid_events(void) gpio_free(OLPC_GPIO_LID); } -static int __devinit setup_power_button(struct platform_device *pdev) +static int setup_power_button(struct platform_device *pdev) { int r; @@ -463,7 +463,7 @@ static void free_power_button(void) input_free_device(power_button_idev); } -static int __devinit setup_ebook_switch(struct platform_device *pdev) +static int setup_ebook_switch(struct platform_device *pdev) { int r; @@ -494,7 +494,7 @@ static void free_ebook_switch(void) input_free_device(ebook_switch_idev); } -static int __devinit setup_lid_switch(struct platform_device *pdev) +static int setup_lid_switch(struct platform_device *pdev) { int r; @@ -538,7 +538,7 @@ static void free_lid_switch(void) input_free_device(lid_switch_idev); } -static int __devinit xo1_sci_probe(struct platform_device *pdev) +static int xo1_sci_probe(struct platform_device *pdev) { struct resource *res; int r; @@ -613,7 +613,7 @@ err_ebook: return r; } -static int __devexit xo1_sci_remove(struct platform_device *pdev) +static int xo1_sci_remove(struct platform_device *pdev) { mfd_cell_disable(pdev); free_irq(sci_irq, pdev); @@ -632,7 +632,7 @@ static struct platform_driver xo1_sci_driver = { .name = "olpc-xo1-sci-acpi", }, .probe = xo1_sci_probe, - .remove = __devexit_p(xo1_sci_remove), + .remove = xo1_sci_remove, .suspend = xo1_sci_suspend, .resume = xo1_sci_resume, }; diff --git a/arch/x86/platform/scx200/scx200_32.c b/arch/x86/platform/scx200/scx200_32.c index 7a9ad30d6c9f..3dc9aee41d91 100644 --- a/arch/x86/platform/scx200/scx200_32.c +++ b/arch/x86/platform/scx200/scx200_32.c @@ -35,7 +35,7 @@ static struct pci_device_id scx200_tbl[] = { }; MODULE_DEVICE_TABLE(pci,scx200_tbl); -static int __devinit scx200_probe(struct pci_dev *, const struct pci_device_id *); +static int scx200_probe(struct pci_dev *, const struct pci_device_id *); static struct pci_driver scx200_pci_driver = { .name = "scx200", @@ -45,7 +45,7 @@ static struct pci_driver scx200_pci_driver = { static DEFINE_MUTEX(scx200_gpio_config_lock); -static void __devinit scx200_init_shadow(void) +static void scx200_init_shadow(void) { int bank; @@ -54,7 +54,7 @@ static void __devinit scx200_init_shadow(void) scx200_gpio_shadow[bank] = inl(scx200_gpio_base + 0x10 * bank); } -static int __devinit scx200_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +static int scx200_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned base; -- cgit v1.2.3 From a706d965dcfdff73bf2bad1c300f8119900714c7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 28 Dec 2012 19:56:07 -0700 Subject: perf x86: revert 20b279 - require exclude_guest to use PEBS - kernel side This patch is brought to you by the letter 'H'. Commit 20b279 breaks compatiblity with older perf binaries when run with precise modifier (:p or :pp) by requiring the exclude_guest attribute to be set. Older binaries default exclude_guest to 0 (ie., wanting guest-based samples) unless host only profiling is requested (:H modifier). The workaround for older binaries is to add H to the modifier list (e.g., -e cycles:ppH - toggles exclude_guest to 1). This was deemed unacceptable by Linus: https://lkml.org/lkml/2012/12/12/570 Between family in town and the fresh snow in Breckenridge there is no time left to be working on the proper fix for this over the holidays. In the New Year I have more pressing problems to resolve -- like some memory leaks in perf which are proving to be elusive -- although the aforementioned snow is probably why they are proving to be elusive. Either way I do not have any spare time to work on this and from the time I have managed to spend on it the solution is more difficult than just moving to a new exclude_guest flag (does not work) or flipping the logic to include_guest (which is not as trivial as one would think). So, two options: silently force exclude_guest on as suggested by Gleb which means no impact to older perf binaries or revert the original patch which caused the breakage. This patch does the latter -- reverts the original patch that introduced the regression. The problem can be revisited in the future as time allows. Signed-off-by: David Ahern Cc: Avi Kivity Cc: Gleb Natapov Cc: Ingo Molnar Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Robert Richter Link: http://lkml.kernel.org/r/1356749767-17322-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- arch/x86/kernel/cpu/perf_event.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4428fd178bce..6774c17a5576 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -340,9 +340,6 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; - - if (!attr->exclude_guest) - return -EOPNOTSUPP; } hwc->config |= config; @@ -385,9 +382,6 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip) { int precise = 0; - if (!event->attr.exclude_guest) - return -EOPNOTSUPP; - /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; -- cgit v1.2.3 From a9acc5365dbda29f7be2884efb63771dc24bd815 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Wed, 14 Nov 2012 20:43:31 +0000 Subject: x86/Sandy Bridge: reserve pages when integrated graphics is present SNB graphics devices have a bug that prevent them from accessing certain memory ranges, namely anything below 1M and in the pages listed in the table. So reserve those at boot if set detect a SNB gfx device on the CPU to avoid GPU hangs. Stephane Marchesin had a similar patch to the page allocator awhile back, but rather than reserving pages up front, it leaked them at allocation time. [ hpa: made a number of stylistic changes, marked arrays as static const, and made less verbose; use "memblock=debug" for full verbosity. ] Signed-off-by: Jesse Barnes Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 23ddd558fbd5..9dcb32545032 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -610,6 +610,81 @@ static __init void reserve_ibft_region(void) static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; +static bool __init snb_gfx_workaround_needed(void) +{ + int i; + u16 vendor, devid; + static const u16 snb_ids[] = { + 0x0102, + 0x0112, + 0x0122, + 0x0106, + 0x0116, + 0x0126, + 0x010a, + }; + + /* Assume no if something weird is going on with PCI */ + if (!early_pci_allowed()) + return false; + + vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID); + if (vendor != 0x8086) + return false; + + devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID); + for (i = 0; i < ARRAY_SIZE(snb_ids); i++) + if (devid == snb_ids[i]) + return true; + + return false; +} + +/* + * Sandy Bridge graphics has trouble with certain ranges, exclude + * them from allocation. + */ +static void __init trim_snb_memory(void) +{ + static const unsigned long bad_pages[] = { + 0x20050000, + 0x20110000, + 0x20130000, + 0x20138000, + 0x40004000, + }; + int i; + + if (!snb_gfx_workaround_needed()) + return; + + printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); + + /* + * Reserve all memory below the 1 MB mark that has not + * already been reserved. + */ + memblock_reserve(0, 1<<20); + + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { + if (memblock_reserve(bad_pages[i], PAGE_SIZE)) + printk(KERN_WARNING "failed to reserve 0x%08lx\n", + bad_pages[i]); + } +} + +/* + * Here we put platform-specific memory range workarounds, i.e. + * memory known to be corrupt or otherwise in need to be reserved on + * specific platforms. + * + * If this gets used more widely it could use a real dispatch mechanism. + */ +static void __init trim_platform_memory_ranges(void) +{ + trim_snb_memory(); +} + static void __init trim_bios_range(void) { /* @@ -630,6 +705,7 @@ static void __init trim_bios_range(void) * take them out. */ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -908,6 +984,8 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); + trim_platform_memory_ranges(); + init_gbpages(); /* max_pfn_mapped is updated here */ -- cgit v1.2.3 From ab3cd8670e0b3fcde7f029e1503ed3c5138e9571 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 13 Jan 2013 20:36:39 -0800 Subject: x86/Sandy Bridge: mark arrays in __init functions as __initconst Mark static arrays as __initconst so they get removed when the init sections are flushed. Reported-by: Mathias Krause Link: http://lkml.kernel.org/r/75F4BEE6-CB0E-4426-B40B-697451677738@googlemail.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 9dcb32545032..18182d19b71b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -614,7 +614,7 @@ static bool __init snb_gfx_workaround_needed(void) { int i; u16 vendor, devid; - static const u16 snb_ids[] = { + static const __initconst u16 snb_ids[] = { 0x0102, 0x0112, 0x0122, @@ -646,7 +646,7 @@ static bool __init snb_gfx_workaround_needed(void) */ static void __init trim_snb_memory(void) { - static const unsigned long bad_pages[] = { + static const __initconst unsigned long bad_pages[] = { 0x20050000, 0x20110000, 0x20130000, -- cgit v1.2.3 From e43b3cec711a61edf047adf6204d542f3a659ef8 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 13 Jan 2013 20:56:41 -0800 Subject: x86/Sandy Bridge: Sandy Bridge workaround depends on CONFIG_PCI early_pci_allowed() and read_pci_config_16() are only available if CONFIG_PCI is defined. Signed-off-by: H. Peter Anvin Cc: Jesse Barnes --- arch/x86/kernel/setup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 18182d19b71b..00f6c1472b85 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -612,6 +612,7 @@ static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; static bool __init snb_gfx_workaround_needed(void) { +#ifdef CONFIG_PCI int i; u16 vendor, devid; static const __initconst u16 snb_ids[] = { @@ -636,6 +637,7 @@ static bool __init snb_gfx_workaround_needed(void) for (i = 0; i < ARRAY_SIZE(snb_ids); i++) if (devid == snb_ids[i]) return true; +#endif return false; } -- cgit v1.2.3 From 9174adbee4a9a49d0139f5d71969852b36720809 Mon Sep 17 00:00:00 2001 From: Andrew Cooper Date: Wed, 16 Jan 2013 12:00:55 +0000 Subject: xen: Fix stack corruption in xen_failsafe_callback for 32bit PVOPS guests. This fixes CVE-2013-0190 / XSA-40 There has been an error on the xen_failsafe_callback path for failed iret, which causes the stack pointer to be wrong when entering the iret_exc error path. This can result in the kernel crashing. In the classic kernel case, the relevant code looked a little like: popl %eax # Error code from hypervisor jz 5f addl $16,%esp jmp iret_exc # Hypervisor said iret fault 5: addl $16,%esp # Hypervisor said segment selector fault Here, there are two identical addls on either option of a branch which appears to have been optimised by hoisting it above the jz, and converting it to an lea, which leaves the flags register unaffected. In the PVOPS case, the code looks like: popl_cfi %eax # Error from the hypervisor lea 16(%esp),%esp # Add $16 before choosing fault path CFI_ADJUST_CFA_OFFSET -16 jz 5f addl $16,%esp # Incorrectly adjust %esp again jmp iret_exc It is possible unprivileged userspace applications to cause this behaviour, for example by loading an LDT code selector, then changing the code selector to be not-present. At this point, there is a race condition where it is possible for the hypervisor to return back to userspace from an interrupt, fault on its own iret, and inject a failsafe_callback into the kernel. This bug has been present since the introduction of Xen PVOPS support in commit 5ead97c84 (xen: Core Xen implementation), in 2.6.23. Signed-off-by: Frediano Ziglio Signed-off-by: Andrew Cooper Cc: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/entry_32.S | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 88b725aa1d52..cf8639b4dcf3 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1084,7 +1084,6 @@ ENTRY(xen_failsafe_callback) lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f - addl $16,%esp jmp iret_exc 5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL -- cgit v1.2.3 From 9899d11f654474d2d54ea52ceaa2a1f4db3abd68 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 21 Jan 2013 20:48:00 +0100 Subject: ptrace: ensure arch_ptrace/ptrace_request can never race with SIGKILL putreg() assumes that the tracee is not running and pt_regs_access() can safely play with its stack. However a killed tracee can return from ptrace_stop() to the low-level asm code and do RESTORE_REST, this means that debugger can actually read/modify the kernel stack until the tracee does SAVE_REST again. set_task_blockstep() can race with SIGKILL too and in some sense this race is even worse, the very fact the tracee can be woken up breaks the logic. As Linus suggested we can clear TASK_WAKEKILL around the arch_ptrace() call, this ensures that nobody can ever wakeup the tracee while the debugger looks at it. Not only this fixes the mentioned problems, we can do some cleanups/simplifications in arch_ptrace() paths. Probably ptrace_unfreeze_traced() needs more callers, for example it makes sense to make the tracee killable for oom-killer before access_process_vm(). While at it, add the comment into may_ptrace_stop() to explain why ptrace_stop() still can't rely on SIGKILL and signal_pending_state(). Reported-by: Salman Qazi Reported-by: Suleiman Souhlal Suggested-by: Linus Torvalds Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- arch/x86/kernel/step.c | 9 +++---- kernel/ptrace.c | 64 ++++++++++++++++++++++++++++++++++++++++++-------- kernel/signal.c | 5 ++++ 3 files changed, 64 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index cd3b2438a980..9b4d51d0c0d0 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -165,10 +165,11 @@ void set_task_blockstep(struct task_struct *task, bool on) * Ensure irq/preemption can't change debugctl in between. * Note also that both TIF_BLOCKSTEP and debugctl should * be changed atomically wrt preemption. - * FIXME: this means that set/clear TIF_BLOCKSTEP is simply - * wrong if task != current, SIGKILL can wakeup the stopped - * tracee and set/clear can play with the running task, this - * can confuse the next __switch_to_xtra(). + * + * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if + * task is current or it can't be running, otherwise we can race + * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but + * PTRACE_KILL is not safe. */ local_irq_disable(); debugctl = get_debugctlmsr(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 62f7c2774b16..6cbeaae4406d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -122,6 +122,40 @@ void __ptrace_unlink(struct task_struct *child) spin_unlock(&child->sighand->siglock); } +/* Ensure that nothing can wake it up, even SIGKILL */ +static bool ptrace_freeze_traced(struct task_struct *task) +{ + bool ret = false; + + /* Lockless, nobody but us can set this flag */ + if (task->jobctl & JOBCTL_LISTENING) + return ret; + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { + task->state = __TASK_TRACED; + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); + + return ret; +} + +static void ptrace_unfreeze_traced(struct task_struct *task) +{ + if (task->state != __TASK_TRACED) + return; + + WARN_ON(!task->ptrace || task->parent != current); + + spin_lock_irq(&task->sighand->siglock); + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + spin_unlock_irq(&task->sighand->siglock); +} + /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for @@ -151,24 +185,29 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); - if ((child->ptrace & PT_PTRACED) && child->parent == current) { + if (child->ptrace && child->parent == current) { + WARN_ON(child->state == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ - spin_lock_irq(&child->sighand->siglock); - WARN_ON_ONCE(task_is_stopped(child)); - if (ignore_state || (task_is_traced(child) && - !(child->jobctl & JOBCTL_LISTENING))) + if (ignore_state || ptrace_freeze_traced(child)) ret = 0; - spin_unlock_irq(&child->sighand->siglock); } read_unlock(&tasklist_lock); - if (!ret && !ignore_state) - ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH; + if (!ret && !ignore_state) { + if (!wait_task_inactive(child, __TASK_TRACED)) { + /* + * This can only happen if may_ptrace_stop() fails and + * ptrace_stop() changes ->state back to TASK_RUNNING, + * so we should not worry about leaking __TASK_TRACED. + */ + WARN_ON(child->state == __TASK_TRACED); + ret = -ESRCH; + } + } - /* All systems go.. */ return ret; } @@ -900,6 +939,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); @@ -1039,8 +1080,11 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); - if (!ret) + if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); + } out_put_task_struct: put_task_struct(child); diff --git a/kernel/signal.c b/kernel/signal.c index 6e97aa6fa32c..3d09cf6cde75 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1794,6 +1794,10 @@ static inline int may_ptrace_stop(void) * If SIGKILL was already sent before the caller unlocked * ->siglock we must see ->core_state != NULL. Otherwise it * is safe to enter schedule(). + * + * This is almost outdated, a task with the pending SIGKILL can't + * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported + * after SIGKILL was already dequeued. */ if (unlikely(current->mm->core_state) && unlikely(current->mm == current->parent->mm)) @@ -1919,6 +1923,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done) do_notify_parent_cldstop(current, false, why); + /* tasklist protects us from ptrace_freeze_traced() */ __set_current_state(TASK_RUNNING); if (clear_code) current->exit_code = 0; -- cgit v1.2.3