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 v1.2.2 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 ++ 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 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(); -- cgit v1.2.2 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 v1.2.2 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 --- arch/x86/kernel/vsyscall_64.c | 110 ++++++++++++++++++++++-------------------- 1 file changed, 59 insertions(+), 51 deletions(-) (limited to 'arch/x86/kernel') 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: -- cgit v1.2.2 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/kernel/cpu/mcheck/mce.c | 97 ++++++++++++++++++++++------------------ 1 file changed, 53 insertions(+), 44 deletions(-) (limited to 'arch/x86/kernel') 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 v1.2.2 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/kernel/cpu/mcheck/mce.c | 51 +++++++++++++++++++++------------------- 1 file changed, 27 insertions(+), 24 deletions(-) (limited to 'arch/x86/kernel') 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 v1.2.2 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/kernel/cpu/mcheck/mce.c | 35 ++++++++++++++++------------------ arch/x86/kernel/cpu/mcheck/mce_intel.c | 2 +- 2 files changed, 17 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') 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 v1.2.2 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/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 +++--- 4 files changed, 21 insertions(+), 27 deletions(-) (limited to 'arch/x86/kernel') 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( -- cgit v1.2.2 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 v1.2.2 From fb50b020c5331c8c4bee0eb875865f5f8be6c03a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:53:09 -0800 Subject: x86: Move some contents of page_64_types.h into pgtable_64.h and page_64.h This patch is meant to clean-up the fact that we have several functions in page_64_types.h which really don't belong there. I found this issue when I had tried to replace __phys_addr with an inline function. It resulted in the realmode bits generating compile warnings about types. In order to resolve that I am relocating the address translation to page_64.h since this is in keeping with where these functions are located in 32 bit. In addtion I have relocated several functions defined in init_64.c to pgtable_64.h as this seems to be where most of the functions related to memory initialization were already located. [ hpa: added missing #include to apic_numachip.c, as reported by Yinghai Lu. ] Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215244.8521.31505.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin Cc: Yinghai Lu Cc: Daniel J Blueman --- arch/x86/kernel/apic/apic_numachip.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index a65829ac2b9a..ae9196f31261 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -27,6 +27,7 @@ #include #include #include +#include static int numachip_system __read_mostly; -- cgit v1.2.2 From 0bdf525f04afd3a32c14e5a8778771f9c9e0f074 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:53:51 -0800 Subject: x86: Improve __phys_addr performance by making use of carry flags and inlining This patch is meant to improve overall system performance when making use of the __phys_addr call. To do this I have implemented several changes. First if CONFIG_DEBUG_VIRTUAL is not defined __phys_addr is made an inline, similar to how this is currently handled in 32 bit. However in order to do this it is required to export phys_base so that it is available if __phys_addr is used in kernel modules. The second change was to streamline the code by making use of the carry flag on an add operation instead of performing a compare on a 64 bit value. The advantage to this is that it allows us to significantly reduce the overall size of the call. On my Xeon E5 system the entire __phys_addr inline call consumes a little less than 32 bytes and 5 instructions. I also applied similar logic to the debug version of the function. My testing shows that the debug version of the function with this patch applied is slightly faster than the non-debug version without the patch. Finally I also applied the same logic changes to __virt_addr_valid since it used the same general code flow as __phys_addr and could achieve similar gains though these changes. Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215315.8521.46270.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/x8664_ksyms_64.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 1330dd102950..b014d9414d08 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -59,6 +59,9 @@ EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(memmove); +#ifndef CONFIG_DEBUG_VIRTUAL +EXPORT_SYMBOL(phys_base); +#endif EXPORT_SYMBOL(empty_zero_page); #ifndef CONFIG_PARAVIRT EXPORT_SYMBOL(native_load_gs_index); -- cgit v1.2.2 From 05a476b6e3795f205806662bf09ab95774266292 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:56:35 -0800 Subject: x86: Drop 4 unnecessary calls to __pa_symbol While debugging the __pa_symbol inline patch I found that there were a couple spots where __pa_symbol was used as follows: __pa_symbol(x) - __pa_symbol(y) The compiler had reduced them to: x - y Since we also support a debug case where __pa_symbol is a function call it would probably be useful to just change the two cases I found so that they are always just treated as "x - y". As such I am casting the values to phys_addr_t and then doing simple subtraction so that the correct type and value is returned. Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215552.8521.68085.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head32.c | 4 ++-- arch/x86/kernel/head64.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index c18f59d10101..f15db0c40713 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -30,8 +30,8 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { - memblock_reserve(__pa_symbol(&_text), - __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); + memblock_reserve(__pa_symbol(_text), + (phys_addr_t)__bss_stop - (phys_addr_t)_text); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 037df57a99ac..42f5df134341 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -97,8 +97,8 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); - memblock_reserve(__pa_symbol(&_text), - __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); + memblock_reserve(__pa_symbol(_text), + (phys_addr_t)__bss_stop - (phys_addr_t)_text); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ -- cgit v1.2.2 From fc8d782677f163dee76427fdd8a92bebd2b50b23 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:57:13 -0800 Subject: x86: Use __pa_symbol instead of __pa on C visible symbols When I made an attempt at separating __pa_symbol and __pa I found that there were a number of cases where __pa was used on an obvious symbol. I also caught one non-obvious case as _brk_start and _brk_end are based on the address of __brk_base which is a C visible symbol. In mark_rodata_ro I was able to reduce the overhead of kernel symbol to virtual memory translation by using a combination of __va(__pa_symbol()) instead of page_address(virt_to_page()). Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215640.8521.80483.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel.c | 2 +- arch/x86/kernel/setup.c | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 198e019a531a..2249e7e44521 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -168,7 +168,7 @@ int __cpuinit ppro_with_ram_bug(void) #ifdef CONFIG_X86_F00F_BUG static void __cpuinit trap_init_f00f_bug(void) { - __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); + __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); /* * Update the IDT descriptor and reload the IDT so that diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ca45696f30fb..2702c5d4acd2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -300,8 +300,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_reserve(__pa(_brk_start), - __pa(_brk_end) - __pa(_brk_start)); + memblock_reserve(__pa_symbol(_brk_start), + _brk_end - _brk_start); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -761,12 +761,12 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) _edata; init_mm.brk = _brk_end; - code_resource.start = virt_to_phys(_text); - code_resource.end = virt_to_phys(_etext)-1; - data_resource.start = virt_to_phys(_etext); - data_resource.end = virt_to_phys(_edata)-1; - bss_resource.start = virt_to_phys(&__bss_start); - bss_resource.end = virt_to_phys(&__bss_stop)-1; + code_resource.start = __pa_symbol(_text); + code_resource.end = __pa_symbol(_etext)-1; + data_resource.start = __pa_symbol(_etext); + data_resource.end = __pa_symbol(_edata)-1; + bss_resource.start = __pa_symbol(__bss_start); + bss_resource.end = __pa_symbol(__bss_stop)-1; #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE -- cgit v1.2.2 From 217f155e9fc68bf2a6c58a7b47e0d1ce68d78818 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:57:32 -0800 Subject: x86/ftrace: Use __pa_symbol instead of __pa on C visible symbols Instead of using __pa which is meant to be a general function for converting virtual addresses to physical addresses we can use __pa_symbol which is the preferred way of decoding kernel text virtual addresses to physical addresses. In this case we are not directly converting C visible symbols however if we know that the instruction pointer is somewhere between _text and _etext we know that we are going to be translating an address form the kernel text space. Cc: Steven Rostedt Cc: Frederic Weisbecker Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215718.8521.24026.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1d414029f1d8..42a392a9fd02 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -89,7 +89,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) * kernel identity mapping to modify code. */ if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa(ip)); + ip = (unsigned long)__va(__pa_symbol(ip)); return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); } @@ -279,7 +279,7 @@ static int ftrace_write(unsigned long ip, const char *val, int size) * kernel identity mapping to modify code. */ if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa(ip)); + ip = (unsigned long)__va(__pa_symbol(ip)); return probe_kernel_write((void *)ip, val, size); } -- cgit v1.2.2 From afd51a0e32cd79261f0e823400886ed322a355ac Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:57:43 -0800 Subject: x86/acpi: Use __pa_symbol instead of __pa on C visible symbols This change just updates one spot where __pa was being used when __pa_symbol should have been used. By using __pa_symbol we are able to drop a few extra lines of code as we don't have to test to see if the virtual pointer is a part of the kernel text or just standard virtual memory. Cc: Len Brown Cc: Pavel Machek Acked-by: "Rafael J. Wysocki" Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215737.8521.51167.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/acpi/sleep.c | 2 +- 1 file changed, 1 insertion(+), 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..f146a3c10814 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -69,7 +69,7 @@ int acpi_suspend_lowlevel(void) #ifndef CONFIG_64BIT header->pmode_entry = (u32)&wakeup_pmode_return; - header->pmode_cr3 = (u32)__pa(&initial_page_table); + header->pmode_cr3 = (u32)__pa_symbol(initial_page_table); saved_magic = 0x12345678; #else /* CONFIG_64BIT */ #ifdef CONFIG_SMP -- cgit v1.2.2 From fa62aafea9e415cd1efd8c4054106112fe809f19 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:38:38 -0800 Subject: x86, mm: Add global page_size_mask and probe one time only Now we pass around use_gbpages and use_pse for calculating page table size, Later we will need to call init_memory_mapping for every ram range one by one, that mean those calculation will be done several times. Those information are the same for all ram range and could be stored in page_size_mask and could be probed it one time only. Move that probing code out of init_memory_mapping into separated function probe_page_size_mask(), and call it before all init_memory_mapping. Suggested-by: Ingo Molnar Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-2-git-send-email-yinghai@kernel.org Reviewed-by: Pekka Enberg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ca45696f30fb..01fb5f9baf90 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -913,6 +913,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); init_gbpages(); + probe_page_size_mask(); /* max_pfn_mapped is updated here */ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn< Date: Fri, 16 Nov 2012 19:38:41 -0800 Subject: x86, mm: Move init_memory_mapping calling out of setup.c Now init_memory_mapping is called two times, later will be called for every ram ranges. Could put all related init_mem calling together and out of setup.c. Actually, it reverts commit 1bbbbe7 x86: Exclude E820_RESERVED regions and memory holes above 4 GB from direct mapping. will address that later with complete solution include handling hole under 4g. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-5-git-send-email-yinghai@kernel.org Reviewed-by: Pekka Enberg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 01fb5f9baf90..23b079fb93fc 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -913,34 +913,9 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); init_gbpages(); - probe_page_size_mask(); - /* max_pfn_mapped is updated here */ - max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn< max_low_pfn) { - int i; - unsigned long start, end; - unsigned long start_pfn, end_pfn; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, - NULL) { - - end = PFN_PHYS(end_pfn); - if (end <= (1UL<<32)) - continue; - - start = PFN_PHYS(start_pfn); - max_pfn_mapped = init_memory_mapping( - max((1UL<<32), start), end); - } - - /* can we preseve max_low_pfn ?*/ - max_low_pfn = max_pfn; - } -#endif memblock.current_limit = get_max_mapped(); dma_contiguous_reserve(0); -- cgit v1.2.2 From dd7dfad7fb297b1746bcdbebbdc970d723a635bd Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:38:46 -0800 Subject: x86, mm: Set memblock initial limit to 1M memblock_x86_fill() could double memory array. If we set memblock.current_limit to 512M, so memory array could be around 512M. So kdump will not get big range (like 512M) under 1024M. Try to put it down under 1M, it would use about 4k or so, and that is limited. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-10-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 23b079fb93fc..4bd89218cbc3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -890,7 +890,7 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); - memblock.current_limit = get_max_mapped(); + memblock.current_limit = ISA_END_ADDRESS; memblock_x86_fill(); /* -- cgit v1.2.2 From 4eea6aa581abfeb2695ebe9f9d4672597e1bdd4b Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Fri, 16 Nov 2012 19:38:47 -0800 Subject: x86, mm: if kernel .text .data .bss are not marked as E820_RAM, complain and fix There could be cases where user supplied memmap=exactmap memory mappings do not mark the region where the kernel .text .data and .bss reside as E820_RAM, as reported here: https://lkml.org/lkml/2012/8/14/86 Handle it by complaining, and adding the range back into the e820. Signed-off-by: Jacob Shin Link: http://lkml.kernel.org/r/1353123563-3103-11-git-send-email-yinghai@kernel.org Signed-off-by: Yinghai Lu Reviewed-by: Pekka Enberg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4bd89218cbc3..d85cbd96525d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -832,6 +832,20 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); + /* + * Complain if .text .data and .bss are not marked as E820_RAM and + * attempt to fix it by adding the range. We may have a confused BIOS, + * or the user may have incorrectly supplied it via memmap=exactmap. If + * we really are running on top non-RAM, we will crash later anyways. + */ + if (!e820_all_mapped(code_resource.start, __pa(__brk_limit), E820_RAM)) { + pr_warn(".text .data .bss are not marked as E820_RAM!\n"); + + e820_add_region(code_resource.start, + __pa(__brk_limit) - code_resource.start + 1, + E820_RAM); + } + trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { -- cgit v1.2.2 From dda56e134059b840631fdfd034784056b627c2a6 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Fri, 16 Nov 2012 19:38:48 -0800 Subject: x86, mm: Fixup code testing if a pfn is direct mapped Update code that previously assumed pfns [ 0 - max_low_pfn_mapped ) and [ 4GB - max_pfn_mapped ) were always direct mapped, to now look up pfn_mapped ranges instead. -v2: change applying sequence to keep git bisecting working. so add dummy pfn_range_is_mapped(). - Yinghai Lu Signed-off-by: Jacob Shin Link: http://lkml.kernel.org/r/1353123563-3103-12-git-send-email-yinghai@kernel.org Signed-off-by: Yinghai Lu Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/amd.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f7e98a2c0d12..9619ba6528ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -676,12 +676,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) * benefit in doing so. */ if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + printk(KERN_DEBUG "tseg: %010llx\n", tseg); - if ((tseg>>PMD_SHIFT) < - (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) || - ((tseg>>PMD_SHIFT) < - (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) && - (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT)))) + if (pfn_range_is_mapped(pfn, pfn + 1)) set_memory_4k((unsigned long)__va(tseg), 1); } } -- cgit v1.2.2 From 5101730cb0613b91d40b9bb7be6bb023d2f6aa24 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:38:50 -0800 Subject: x86, mm: use pfn_range_is_mapped() with gart We are going to map ram only, so under max_low_pfn_mapped, between 4g and max_pfn_mapped does not mean mapped at all. Use pfn_range_is_mapped() directly. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-14-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/amd_gart_64.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index e66311200cbd..b574b295a2f9 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -768,10 +768,9 @@ int __init gart_iommu_init(void) aper_base = info.aper_base; end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); - if (end_pfn > max_low_pfn_mapped) { - start_pfn = (aper_base>>PAGE_SHIFT); + start_pfn = PFN_DOWN(aper_base); + if (!pfn_range_is_mapped(start_pfn, end_pfn)) init_memory_mapping(start_pfn< Date: Fri, 16 Nov 2012 19:38:51 -0800 Subject: x86, mm: use pfn_range_is_mapped() with reserve_initrd We are going to map ram only, so under max_low_pfn_mapped, between 4g and max_pfn_mapped does not mean mapped at all. Use pfn_range_is_mapped() to find out if range is mapped for initrd. That could happen bootloader put initrd in range but user could use memmap to carve some of range out. Also during copying need to use early_memmap to map original initrd for accessing. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-15-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 52 ++++++++++++++++++++++++++----------------------- 1 file changed, 28 insertions(+), 24 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d85cbd96525d..bd52f9da17cc 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -317,20 +317,19 @@ static void __init relocate_initrd(void) u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; u64 area_size = PAGE_ALIGN(ramdisk_size); - u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; u64 ramdisk_here; unsigned long slop, clen, mapaddr; char *p, *q; - /* We need to move the initrd down into lowmem */ - ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size, - PAGE_SIZE); + /* We need to move the initrd down into directly mapped mem */ + ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_low_pfn_mapped), + area_size, PAGE_SIZE); if (!ramdisk_here) panic("Cannot find place for new RAMDISK of size %lld\n", ramdisk_size); - /* Note: this includes all the lowmem currently occupied by + /* Note: this includes all the mem currently occupied by the initrd, we rely on that fact to keep the data intact. */ memblock_reserve(ramdisk_here, area_size); initrd_start = ramdisk_here + PAGE_OFFSET; @@ -340,17 +339,7 @@ static void __init relocate_initrd(void) q = (char *)initrd_start; - /* Copy any lowmem portion of the initrd */ - if (ramdisk_image < end_of_lowmem) { - clen = end_of_lowmem - ramdisk_image; - p = (char *)__va(ramdisk_image); - memcpy(q, p, clen); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } - - /* Copy the highmem portion of the initrd */ + /* Copy the initrd */ while (ramdisk_size) { slop = ramdisk_image & ~PAGE_MASK; clen = ramdisk_size; @@ -364,7 +353,7 @@ static void __init relocate_initrd(void) ramdisk_image += clen; ramdisk_size -= clen; } - /* high pages is not converted by early_res_to_bootmem */ + ramdisk_image = boot_params.hdr.ramdisk_image; ramdisk_size = boot_params.hdr.ramdisk_size; printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" @@ -373,13 +362,27 @@ static void __init relocate_initrd(void) ramdisk_here, ramdisk_here + ramdisk_size - 1); } +static u64 __init get_mem_size(unsigned long limit_pfn) +{ + int i; + u64 mapped_pages = 0; + unsigned long start_pfn, end_pfn; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + start_pfn = min_t(unsigned long, start_pfn, limit_pfn); + end_pfn = min_t(unsigned long, end_pfn, limit_pfn); + mapped_pages += end_pfn - start_pfn; + } + + return mapped_pages << PAGE_SHIFT; +} static void __init reserve_initrd(void) { /* Assume only end is not page aligned */ u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; + u64 mapped_size; if (!boot_params.hdr.type_of_loader || !ramdisk_image || !ramdisk_size) @@ -387,18 +390,19 @@ static void __init reserve_initrd(void) initrd_start = 0; - if (ramdisk_size >= (end_of_lowmem>>1)) { + mapped_size = get_mem_size(max_low_pfn_mapped); + if (ramdisk_size >= (mapped_size>>1)) panic("initrd too large to handle, " "disabling initrd (%lld needed, %lld available)\n", - ramdisk_size, end_of_lowmem>>1); - } + ramdisk_size, mapped_size>>1); printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_end - 1); - - if (ramdisk_end <= end_of_lowmem) { - /* All in lowmem, easy case */ + if (ramdisk_end <= (max_low_pfn_mapped< Date: Fri, 16 Nov 2012 19:38:52 -0800 Subject: x86, mm: Only direct map addresses that are marked as E820_RAM Currently direct mappings are created for [ 0 to max_low_pfn< Link: http://lkml.kernel.org/r/1353123563-3103-16-git-send-email-yinghai@kernel.org Signed-off-by: Yinghai Lu Reviewed-by: Pekka Enberg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bd52f9da17cc..68dffeceb193 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -116,9 +116,11 @@ #include /* - * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. - * The direct mapping extends to max_pfn_mapped, so that we can directly access - * apertures, ACPI and other tables without having to play with fixmaps. + * max_low_pfn_mapped: highest direct mapped pfn under 4GB + * max_pfn_mapped: highest direct mapped pfn over 4GB + * + * The direct mapping only covers E820_RAM regions, so the ranges and gaps are + * represented by pfn_mapped */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; -- cgit v1.2.2 From 74f27655dda84604d8bab47872020dcce5c88731 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:38:53 -0800 Subject: x86, mm: relocate initrd under all mem for 64bit instead of under 4g. For 64bit, we can use any mapped mem instead of low mem. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-17-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 68dffeceb193..94f922a73c54 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -324,7 +324,7 @@ static void __init relocate_initrd(void) char *p, *q; /* We need to move the initrd down into directly mapped mem */ - ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_low_pfn_mapped), + ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), area_size, PAGE_SIZE); if (!ramdisk_here) @@ -392,7 +392,7 @@ static void __init reserve_initrd(void) initrd_start = 0; - mapped_size = get_mem_size(max_low_pfn_mapped); + mapped_size = get_mem_size(max_pfn_mapped); if (ramdisk_size >= (mapped_size>>1)) panic("initrd too large to handle, " "disabling initrd (%lld needed, %lld available)\n", @@ -401,8 +401,7 @@ static void __init reserve_initrd(void) printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_end - 1); - if (ramdisk_end <= (max_low_pfn_mapped< Date: Fri, 16 Nov 2012 19:38:58 -0800 Subject: x86, mm: setup page table in top-down Get pgt_buf early from BRK, and use it to map PMD_SIZE from top at first. Then use mapped pages to map more ranges below, and keep looping until all pages get mapped. alloc_low_page will use page from BRK at first, after that buffer is used up, will use memblock to find and reserve pages for page table usage. Introduce min_pfn_mapped to make sure find new pages from mapped ranges, that will be updated when lower pages get mapped. Also add step_size to make sure that don't try to map too big range with limited mapped pages initially, and increase the step_size when we have more mapped pages on hand. We don't need to call pagetable_reserve anymore, reserve work is done in alloc_low_page() directly. At last we can get rid of calculation and find early pgt related code. -v2: update to after fix_xen change, also use MACRO for initial pgt_buf size and add comments with it. -v3: skip big reserved range in memblock.reserved near end. -v4: don't need fix_xen change now. -v5: add changelog about moving about reserving pagetable to alloc_low_page. Suggested-by: "H. Peter Anvin" Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-22-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 94f922a73c54..f7634092931b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -124,6 +124,7 @@ */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; +unsigned long min_pfn_mapped; #ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); @@ -900,6 +901,8 @@ void __init setup_arch(char **cmdline_p) reserve_ibft_region(); + early_alloc_pgt_buf(); + /* * Need to conclude brk, before memblock_x86_fill() * it could use memblock_find_in_range, could overlap with -- cgit v1.2.2 From 9985b4c6fa7d660f685918a58282275e9e35d8e0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:02 -0800 Subject: x86, mm: Move min_pfn_mapped back to mm/init.c Also change it to static. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-26-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7634092931b..20151941cce8 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -124,7 +124,6 @@ */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; -unsigned long min_pfn_mapped; #ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); -- cgit v1.2.2 From 6f80b68e9e515547edbacb0c37491730bf766db5 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:03 -0800 Subject: x86, mm, Xen: Remove mapping_pagetable_reserve() Page table area are pre-mapped now after x86, mm: setup page table in top-down x86, mm: Remove early_memremap workaround for page table accessing on 64bit mapping_pagetable_reserve is not used anymore, so remove it. Also remove operation in mask_rw_pte(), as modified allow_low_page always return pages that are already mapped, moreover xen_alloc_pte_init, xen_alloc_pmd_init, etc, will mark the page RO before hooking it into the pagetable automatically. -v2: add changelog about mask_rw_pte() from Stefano. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-27-git-send-email-yinghai@kernel.org Cc: Stefano Stabellini Signed-off-by: H. Peter Anvin --- arch/x86/kernel/x86_init.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 7a3d075a814a..50cf83ecd32e 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -62,10 +62,6 @@ struct x86_init_ops x86_init __initdata = { .banner = default_banner, }, - .mapping = { - .pagetable_reserve = native_pagetable_reserve, - }, - .paging = { .pagetable_init = native_pagetable_init, }, -- cgit v1.2.2 From 148b20989e0b83cb301e1fcd9e987c7abde05333 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:08 -0800 Subject: x86, mm: Move init_gbpages() out of setup.c Put it in mm/init.c, and call it from probe_page_mask(). init_mem_mapping is calling probe_page_mask at first. So calling sequence is not changed. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-32-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 20151941cce8..85b62f1c8071 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -282,18 +282,7 @@ void * __init extend_brk(size_t size, size_t align) return ret; } -#ifdef CONFIG_X86_64 -static void __init init_gbpages(void) -{ - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -} -#else -static inline void init_gbpages(void) -{ -} +#ifdef CONFIG_X86_32 static void __init cleanup_highmap(void) { } @@ -933,8 +922,6 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); - init_gbpages(); - init_mem_mapping(); memblock.current_limit = get_max_mapped(); -- cgit v1.2.2 From c074eaac2ab264c94520efff7e896b771de885ae Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:20 -0800 Subject: x86, mm: kill numa_64.h Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-44-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/acpi/boot.c | 1 - arch/x86/kernel/cpu/amd.c | 1 - arch/x86/kernel/cpu/intel.c | 1 - arch/x86/kernel/setup.c | 3 --- 4 files changed, 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e651f7a589ac..4b23aa18518d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -51,7 +51,6 @@ EXPORT_SYMBOL(acpi_disabled); #ifdef CONFIG_X86_64 # include -# include #endif /* X86 */ #define BAD_MADT_ENTRY(entry, end) ( \ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9619ba6528ca..913f94f9e8d9 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -12,7 +12,6 @@ #include #ifdef CONFIG_X86_64 -# include # include # include #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 198e019a531a..3b547cc4bd03 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -17,7 +17,6 @@ #ifdef CONFIG_X86_64 #include -#include #endif #include "cpu.h" diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 85b62f1c8071..6d29d1fcf068 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -108,9 +108,6 @@ #include #include #include -#ifdef CONFIG_X86_64 -#include -#endif #include #include #include -- cgit v1.2.2 From 9710f581bb4c35589ac046b0cfc0deb7f369fc85 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:23 -0800 Subject: x86, mm: Let "memmap=" take more entries one time Current "memmap=" only can take one entry every time. when we have more entries, we have to use memmap= for each of them. For pxe booting, we have command line length limitation, those extra "memmap=" would waste too much space. This patch make memmap= could take several entries one time, and those entries will be split with ',' Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-47-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/e820.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index df06ade26bef..d32abeabbda5 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -835,7 +835,7 @@ static int __init parse_memopt(char *p) } early_param("mem", parse_memopt); -static int __init parse_memmap_opt(char *p) +static int __init parse_memmap_one(char *p) { char *oldp; u64 start_at, mem_size; @@ -877,6 +877,20 @@ static int __init parse_memmap_opt(char *p) return *p == '\0' ? 0 : -EINVAL; } +static int __init parse_memmap_opt(char *str) +{ + while (str) { + char *k = strchr(str, ','); + + if (k) + *k++ = 0; + + parse_memmap_one(str); + str = k; + } + + return 0; +} early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) -- cgit v1.2.2 From bbee3aec3472fc2ca10b6b1020aec84567ea25ce Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 19 Nov 2012 10:31:37 -0800 Subject: x86: Fix warning about cast from pointer to integer of different size This patch fixes a warning reported by the kbuild test robot where we were casting a pointer to a physical address which represents an integer of a different size. Per the suggestion of Peter Anvin I am replacing it and one other spot where I made a similar cast with an unsigned long. Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121119182927.3655.7641.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head32.c | 2 +- arch/x86/kernel/head64.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index f15db0c40713..e17554832991 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -31,7 +31,7 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { memblock_reserve(__pa_symbol(_text), - (phys_addr_t)__bss_stop - (phys_addr_t)_text); + (unsigned long)__bss_stop - (unsigned long)_text); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 42f5df134341..7b215a50ec1e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -98,7 +98,7 @@ void __init x86_64_start_reservations(char *real_mode_data) copy_bootdata(__va(real_mode_data)); memblock_reserve(__pa_symbol(_text), - (phys_addr_t)__bss_stop - (phys_addr_t)_text); + (unsigned long)__bss_stop - (unsigned long)_text); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ -- cgit v1.2.2 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/kernel/tboot.c | 78 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 73 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') 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); -- cgit v1.2.2 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 v1.2.2 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 v1.2.2 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/x86/kernel/entry_32.S | 1 - arch/x86/kernel/entry_64.S | 1 - arch/x86/kernel/signal.c | 7 ------- 3 files changed, 9 deletions(-) (limited to 'arch/x86/kernel') 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. */ -- cgit v1.2.2 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/kernel/entry_64.S | 2 -- arch/x86/kernel/signal.c | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'arch/x86/kernel') 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; -- cgit v1.2.2 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/kernel/signal.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') 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; -- cgit v1.2.2 From 8f170faeb458532282dbfa870f456e42c11d1ebb Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 20 Dec 2012 14:11:36 -0500 Subject: x86, apb_timer: remove unused variable percpu_timer Signed-off-by: Sasha Levin Link: http://lkml.kernel.org/r/1356030701-16284-28-git-send-email-sasha.levin@oracle.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apb_timer.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index afdc3f756dea..cc74fd0c90f2 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -311,7 +311,6 @@ void __init apbt_time_init(void) #ifdef CONFIG_SMP int i; struct sfi_timer_table_entry *p_mtmr; - unsigned int percpu_timer; struct apbt_dev *adev; #endif @@ -346,13 +345,10 @@ void __init apbt_time_init(void) return; } pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus()); - if (num_possible_cpus() <= sfi_mtimer_num) { - percpu_timer = 1; + if (num_possible_cpus() <= sfi_mtimer_num) apbt_num_timers_used = num_possible_cpus(); - } else { - percpu_timer = 0; + else apbt_num_timers_used = 1; - } pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used); /* here we set up per CPU timer data structure */ -- cgit v1.2.2 From 4d899be584d4b4c5d6b49d655176b25cebf6ff1a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 21 Dec 2012 17:57:05 -0800 Subject: x86/mce: don't use [delayed_]work_pending() There's no need to test whether a (delayed) work item in pending before queueing, flushing or cancelling it. Most uses are unnecessary and quite a few of them are buggy. Remove unnecessary pending tests from x86/mce. Only compile tested. v2: Local var work removed from mce_schedule_work() as suggested by Borislav. Signed-off-by: Tejun Heo Acked-by: Borislav Petkov Cc: Tony Luck Cc: linux-edac@vger.kernel.org --- arch/x86/kernel/cpu/mcheck/mce.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 80dbda84f1c3..fc7608a89d93 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -512,11 +512,8 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { - if (!mce_ring_empty()) { - struct work_struct *work = &__get_cpu_var(mce_work); - if (!work_pending(work)) - schedule_work(work); - } + if (!mce_ring_empty()) + schedule_work(&__get_cpu_var(mce_work)); } DEFINE_PER_CPU(struct irq_work, mce_irq_work); @@ -1351,12 +1348,7 @@ int mce_notify_irq(void) /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); - /* - * There is no risk of missing notifications because - * work_pending is always cleared before the function is - * executed. - */ - if (mce_helper[0] && !work_pending(&mce_trigger_work)) + if (mce_helper[0]) schedule_work(&mce_trigger_work); if (__ratelimit(&ratelimit)) -- cgit v1.2.2 From d82603c6da7579c50ebe3fe7da6e3e267d9f6427 Mon Sep 17 00:00:00 2001 From: Jorrit Schippers Date: Thu, 27 Dec 2012 17:33:02 +0100 Subject: treewide: Replace incomming with incoming in all comments and strings Signed-off-by: Jorrit Schippers Signed-off-by: Jiri Kosina --- arch/x86/kernel/cpu/perf_event_amd_ibs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 6336bcbd0618..5f0581e713c2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -528,7 +528,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) if (!test_bit(IBS_STARTED, pcpu->state)) { /* * Catch spurious interrupts after stopping IBS: After - * disabling IBS there could be still incomming NMIs + * disabling IBS there could be still incoming NMIs * with samples that even have the valid bit cleared. * Mark all this NMIs as handled. */ -- cgit v1.2.2 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/kernel/cpu/perf_event_intel_uncore.c | 6 +++--- arch/x86/kernel/pci-dma.c | 2 +- arch/x86/kernel/quirks.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') 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; -- cgit v1.2.2 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 v1.2.2 From 8b84c8df38d5796da2e8cd051666d203ddabcb62 Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Tue, 27 Nov 2012 14:32:10 +0800 Subject: x86, AMD, NB: Use u16 for northbridge IDs in amd_get_nb_id Change amd_get_nb_id to return u16 to support >255 memory controllers, and related consistency fixes. Signed-off-by: Daniel J Blueman Link: http://lkml.kernel.org/r/1353997932-8475-2-git-send-email-daniel@numascale-asia.com Signed-off-by: Borislav Petkov --- arch/x86/kernel/cpu/amd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15239fffd6fe..782c456eaa01 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -364,9 +364,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) #endif } -int amd_get_nb_id(int cpu) +u16 amd_get_nb_id(int cpu) { - int id = 0; + u16 id = 0; #ifdef CONFIG_SMP id = per_cpu(cpu_llc_id, cpu); #endif -- cgit v1.2.2 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 v1.2.2 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 v1.2.2 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 v1.2.2 From 2353b47bffe4e6ab39042f470c55d41bb3ff3846 Mon Sep 17 00:00:00 2001 From: Bernd Faust Date: Wed, 5 Dec 2012 15:16:49 +0100 Subject: Round the calculated scale factor in set_cyc2ns_scale() During some experiments with an external clock (in a FPGA), we saw that the TSC clock drifted approx. 2.5ms per second. This drift was caused by the current way of calculating the scale. In our case cpu_khz had a value of 3292725. This resulted in a scale value of 310. But when doing the calculation by hand it shows that the actual value is 310.9886188491, so a value of 311 would be more precise. With this change the value is rounded. Signed-off-by: Bernd Faust Signed-off-by: John Stultz --- arch/x86/kernel/tsc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cfa5d4f7ca56..8ed085733773 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -617,7 +617,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) ns_now = __cycles_2_ns(tsc_now); if (cpu_khz) { - *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; + *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + + cpu_khz / 2) / cpu_khz; *offset = ns_now - mult_frac(tsc_now, *scale, (1UL << CYC2NS_SCALE_FACTOR)); } -- cgit v1.2.2 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 v1.2.2 From 29c6fb7be156ae3c0e202c3903087ab6e57d3ad3 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 4 Jan 2013 11:12:44 +0000 Subject: x86/nmi: export local_touch_nmi() symbol for modules Signed-off-by: Jacob Pan Signed-off-by: Zhang Rui --- arch/x86/kernel/nmi.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index f84f5c57de35..60308053fdb2 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -509,3 +509,4 @@ void local_touch_nmi(void) { __this_cpu_write(last_nmi_rip, 0); } +EXPORT_SYMBOL_GPL(local_touch_nmi); -- cgit v1.2.2 From 021ef050fc092d5638e69868d126c18006ea7296 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sat, 19 Jan 2013 10:29:37 -0800 Subject: x86-32: Start out cr0 clean, disable paging before modifying cr3/4 Patch 5a5a51db78e x86-32: Start out eflags and cr4 clean ... made x86-32 match x86-64 in that we initialize %eflags and %cr4 from scratch. This broke OLPC XO-1.5, because the XO enters the kernel with paging enabled, which the kernel doesn't expect. Since we no longer support 386 (the source of most of the variability in %cr0 configuration), we can simply match further x86-64 and initialize %cr0 to a fixed value -- the one variable part remaining in %cr0 is for FPU control, but all that is handled later on in initialization; in particular, configuring %cr0 as if the FPU is present until proven otherwise is correct and necessary for the probe to work. To deal with the XO case sanely, explicitly disable paging in %cr0 before we muck with %cr3, %cr4 or EFER -- those operations are inherently unsafe with paging enabled. NOTE: There is still a lot of 386-related junk in head_32.S which we can and should get rid of, however, this is intended as a minimal fix whereas the cleanup can be deferred to the next merge window. Reported-by: Andres Salomon Tested-by: Daniel Drake Link: http://lkml.kernel.org/r/50FA0661.2060400@linux.intel.com 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 8e7f6556028f..c8932c79e78b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -300,6 +300,12 @@ ENTRY(startup_32_smp) leal -__PAGE_OFFSET(%ecx),%esp default_entry: +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) + movl $(CR0_STATE & ~X86_CR0_PG),%eax + movl %eax,%cr0 + /* * New page tables may be in 4Mbyte page mode and may * be using the global pages. @@ -364,8 +370,7 @@ default_entry: */ movl $pa(initial_page_table), %eax movl %eax,%cr3 /* set the page table pointer.. */ - movl %cr0,%eax - orl $X86_CR0_PG,%eax + movl $CR0_STATE,%eax movl %eax,%cr0 /* ..and set paging (PG) bit */ ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */ 1: -- cgit v1.2.2 From 373d4d099761cb1f637bed488ab3871945882273 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 21 Jan 2013 17:17:39 +1030 Subject: taint: add explicit flag to show whether lock dep is still OK. Fix up all callers as they were before, with make one change: an unsigned module taints the kernel, but doesn't turn off lockdep. Signed-off-by: Rusty Russell --- arch/x86/kernel/cpu/amd.c | 3 +-- arch/x86/kernel/cpu/mcheck/mce.c | 2 +- arch/x86/kernel/cpu/mcheck/p5.c | 2 +- arch/x86/kernel/cpu/mcheck/winchip.c | 2 +- arch/x86/kernel/cpu/mtrr/generic.c | 2 +- arch/x86/kernel/dumpstack.c | 2 +- 6 files changed, 6 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15239fffd6fe..5853e57523e5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -220,8 +220,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) */ WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); - if (!test_taint(TAINT_UNSAFE_SMP)) - add_taint(TAINT_UNSAFE_SMP); + add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); valid_k7: ; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 80dbda84f1c3..6bc15edbc8cd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1085,7 +1085,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* * Set taint even when machine check was not enabled. */ - add_taint(TAINT_MACHINE_CHECK); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); severity = mce_severity(&m, cfg->tolerant, NULL); diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 2d5454cd2c4f..1c044b1ccc59 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -33,7 +33,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) smp_processor_id()); } - add_taint(TAINT_MACHINE_CHECK); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 2d7998fb628c..e9a701aecaa1 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -15,7 +15,7 @@ static void winchip_machine_check(struct pt_regs *regs, long error_code) { printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); - add_taint(TAINT_MACHINE_CHECK); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index e9fe907cd249..fa72a39e5d46 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -542,7 +542,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, if (tmp != mask_lo) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); - add_taint(TAINT_FIRMWARE_WORKAROUND); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); mask_lo = tmp; } } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ae42418bc50f..c8797d55b245 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -232,7 +232,7 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) bust_spinlocks(0); die_owner = -1; - add_taint(TAINT_DIE); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); die_nest_count--; if (!die_nest_count) /* Nest count reaches zero, release the lock. */ -- cgit v1.2.2 From e7dbfe349d12eabb7783b117e0c115f6f3d9ef9e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 28 Sep 2012 17:15:20 +0900 Subject: kprobes/x86: Move ftrace-based kprobe code into kprobes-ftrace.c Split ftrace-based kprobes code from kprobes, and introduce CONFIG_(HAVE_)KPROBES_ON_FTRACE Kconfig flags. For the cleanup reason, this also moves kprobe_ftrace check into skip_singlestep. Link: http://lkml.kernel.org/r/20120928081520.3560.25624.stgit@ltc138.sdl.hitachi.co.jp Cc: Ingo Molnar Cc: Ananth N Mavinakayanahalli Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Frederic Weisbecker Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- arch/x86/kernel/Makefile | 1 + arch/x86/kernel/kprobes-common.h | 11 +++++ arch/x86/kernel/kprobes-ftrace.c | 93 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/kprobes.c | 70 +----------------------------- 4 files changed, 107 insertions(+), 68 deletions(-) create mode 100644 arch/x86/kernel/kprobes-ftrace.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 34e923a53762..cc5d31f8830c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_OPTPROBES) += kprobes-opt.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h index 3230b68ef29a..2e9d4b5af036 100644 --- a/arch/x86/kernel/kprobes-common.h +++ b/arch/x86/kernel/kprobes-common.h @@ -99,4 +99,15 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig return addr; } #endif + +#ifdef CONFIG_KPROBES_ON_FTRACE +extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb); +#else +static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + return 0; +} +#endif #endif diff --git a/arch/x86/kernel/kprobes-ftrace.c b/arch/x86/kernel/kprobes-ftrace.c new file mode 100644 index 000000000000..70a81c7aa0a7 --- /dev/null +++ b/arch/x86/kernel/kprobes-ftrace.c @@ -0,0 +1,93 @@ +/* + * Dynamic Ftrace based Kprobes Optimization + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) Hitachi Ltd., 2012 + */ +#include +#include +#include +#include +#include + +#include "kprobes-common.h" + +static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); + return 1; +} + +int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + if (kprobe_ftrace(p)) + return __skip_singlestep(p, regs, kcb); + else + return 0; +} + +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + __skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 57916c0d3cf6..18114bfb10f3 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -541,23 +541,6 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } -#ifdef KPROBES_CAN_USE_FTRACE -static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); -} -#endif - /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -616,13 +599,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { -#ifdef KPROBES_CAN_USE_FTRACE - if (kprobe_ftrace(p)) { - skip_singlestep(p, regs, kcb); - return 1; - } -#endif - setup_singlestep(p, regs, kcb, 0); + if (!skip_singlestep(p, regs, kcb)) + setup_singlestep(p, regs, kcb, 0); return 1; } } /* else: not a kprobe fault; let the kernel handle it */ @@ -1075,50 +1053,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } -#ifdef KPROBES_CAN_USE_FTRACE -/* Ftrace callback handler for kprobes */ -void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) -{ - struct kprobe *p; - struct kprobe_ctlblk *kcb; - unsigned long flags; - - /* Disable irq for emulating a breakpoint and avoiding preempt */ - local_irq_save(flags); - - p = get_kprobe((kprobe_opcode_t *)ip); - if (unlikely(!p) || kprobe_disabled(p)) - goto end; - - kcb = get_kprobe_ctlblk(); - if (kprobe_running()) { - kprobes_inc_nmissed_count(p); - } else { - /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ - regs->ip = ip + sizeof(kprobe_opcode_t); - - __this_cpu_write(current_kprobe, p); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - skip_singlestep(p, regs, kcb); - /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. - */ - } -end: - local_irq_restore(flags); -} - -int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) -{ - p->ainsn.insn = NULL; - p->ainsn.boostable = -1; - return 0; -} -#endif - int __init arch_init_kprobes(void) { return arch_init_optprobes(); -- cgit v1.2.2 From f684199f5de805ac50ea5bdec2b082882586a777 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 28 Sep 2012 17:15:22 +0900 Subject: kprobes/x86: Move kprobes stuff under arch/x86/kernel/kprobes/ Move arch-dep kprobes stuff under arch/x86/kernel/kprobes. Link: http://lkml.kernel.org/r/20120928081522.3560.75469.stgit@ltc138.sdl.hitachi.co.jp Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Masami Hiramatsu [ fixed whitespace and s/__attribute__((packed))/__packed/ ] Signed-off-by: Steven Rostedt --- arch/x86/kernel/Makefile | 4 +- arch/x86/kernel/kprobes-common.h | 113 ---- arch/x86/kernel/kprobes-ftrace.c | 93 ---- arch/x86/kernel/kprobes-opt.c | 512 ------------------ arch/x86/kernel/kprobes.c | 1064 -------------------------------------- arch/x86/kernel/kprobes/Makefile | 7 + arch/x86/kernel/kprobes/common.h | 113 ++++ arch/x86/kernel/kprobes/core.c | 1064 ++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/kprobes/ftrace.c | 93 ++++ arch/x86/kernel/kprobes/opt.c | 512 ++++++++++++++++++ 10 files changed, 1790 insertions(+), 1785 deletions(-) delete mode 100644 arch/x86/kernel/kprobes-common.h delete mode 100644 arch/x86/kernel/kprobes-ftrace.c delete mode 100644 arch/x86/kernel/kprobes-opt.c delete mode 100644 arch/x86/kernel/kprobes.c create mode 100644 arch/x86/kernel/kprobes/Makefile create mode 100644 arch/x86/kernel/kprobes/common.h create mode 100644 arch/x86/kernel/kprobes/core.c create mode 100644 arch/x86/kernel/kprobes/ftrace.c create mode 100644 arch/x86/kernel/kprobes/opt.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index cc5d31f8830c..ac3b3d002833 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -65,9 +65,7 @@ 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 -obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_OPTPROBES) += kprobes-opt.o -obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o +obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h deleted file mode 100644 index 2e9d4b5af036..000000000000 --- a/arch/x86/kernel/kprobes-common.h +++ /dev/null @@ -1,113 +0,0 @@ -#ifndef __X86_KERNEL_KPROBES_COMMON_H -#define __X86_KERNEL_KPROBES_COMMON_H - -/* Kprobes and Optprobes common header */ - -#ifdef CONFIG_X86_64 -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax. */ \ - " subq $24, %rsp\n" \ - " pushq %rdi\n" \ - " pushq %rsi\n" \ - " pushq %rdx\n" \ - " pushq %rcx\n" \ - " pushq %rax\n" \ - " pushq %r8\n" \ - " pushq %r9\n" \ - " pushq %r10\n" \ - " pushq %r11\n" \ - " pushq %rbx\n" \ - " pushq %rbp\n" \ - " pushq %r12\n" \ - " pushq %r13\n" \ - " pushq %r14\n" \ - " pushq %r15\n" -#define RESTORE_REGS_STRING \ - " popq %r15\n" \ - " popq %r14\n" \ - " popq %r13\n" \ - " popq %r12\n" \ - " popq %rbp\n" \ - " popq %rbx\n" \ - " popq %r11\n" \ - " popq %r10\n" \ - " popq %r9\n" \ - " popq %r8\n" \ - " popq %rax\n" \ - " popq %rcx\n" \ - " popq %rdx\n" \ - " popq %rsi\n" \ - " popq %rdi\n" \ - /* Skip orig_ax, ip, cs */ \ - " addq $24, %rsp\n" -#else -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax and gs. */ \ - " subl $16, %esp\n" \ - " pushl %fs\n" \ - " pushl %es\n" \ - " pushl %ds\n" \ - " pushl %eax\n" \ - " pushl %ebp\n" \ - " pushl %edi\n" \ - " pushl %esi\n" \ - " pushl %edx\n" \ - " pushl %ecx\n" \ - " pushl %ebx\n" -#define RESTORE_REGS_STRING \ - " popl %ebx\n" \ - " popl %ecx\n" \ - " popl %edx\n" \ - " popl %esi\n" \ - " popl %edi\n" \ - " popl %ebp\n" \ - " popl %eax\n" \ - /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ - " addl $24, %esp\n" -#endif - -/* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction); -/* Recover instruction if given address is probed */ -extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, - unsigned long addr); -/* - * Copy an instruction and adjust the displacement if the instruction - * uses the %rip-relative addressing mode. - */ -extern int __copy_instruction(u8 *dest, u8 *src); - -/* Generate a relative-jump/call instruction */ -extern void synthesize_reljump(void *from, void *to); -extern void synthesize_relcall(void *from, void *to); - -#ifdef CONFIG_OPTPROBES -extern int arch_init_optprobes(void); -extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); -extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); -#else /* !CONFIG_OPTPROBES */ -static inline int arch_init_optprobes(void) -{ - return 0; -} -static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) -{ - return 0; -} -static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) -{ - return addr; -} -#endif - -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif -#endif diff --git a/arch/x86/kernel/kprobes-ftrace.c b/arch/x86/kernel/kprobes-ftrace.c deleted file mode 100644 index 70a81c7aa0a7..000000000000 --- a/arch/x86/kernel/kprobes-ftrace.c +++ /dev/null @@ -1,93 +0,0 @@ -/* - * Dynamic Ftrace based Kprobes Optimization - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) Hitachi Ltd., 2012 - */ -#include -#include -#include -#include -#include - -#include "kprobes-common.h" - -static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - return 1; -} - -int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb); - else - return 0; -} - -/* Ftrace callback handler for kprobes */ -void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) -{ - struct kprobe *p; - struct kprobe_ctlblk *kcb; - unsigned long flags; - - /* Disable irq for emulating a breakpoint and avoiding preempt */ - local_irq_save(flags); - - p = get_kprobe((kprobe_opcode_t *)ip); - if (unlikely(!p) || kprobe_disabled(p)) - goto end; - - kcb = get_kprobe_ctlblk(); - if (kprobe_running()) { - kprobes_inc_nmissed_count(p); - } else { - /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ - regs->ip = ip + sizeof(kprobe_opcode_t); - - __this_cpu_write(current_kprobe, p); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - __skip_singlestep(p, regs, kcb); - /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. - */ - } -end: - local_irq_restore(flags); -} - -int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) -{ - p->ainsn.insn = NULL; - p->ainsn.boostable = -1; - return 0; -} diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c deleted file mode 100644 index c5e410eed403..000000000000 --- a/arch/x86/kernel/kprobes-opt.c +++ /dev/null @@ -1,512 +0,0 @@ -/* - * Kernel Probes Jump Optimization (Optprobes) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) IBM Corporation, 2002, 2004 - * Copyright (C) Hitachi Ltd., 2012 - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#include "kprobes-common.h" - -unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) -{ - struct optimized_kprobe *op; - struct kprobe *kp; - long offs; - int i; - - for (i = 0; i < RELATIVEJUMP_SIZE; i++) { - kp = get_kprobe((void *)addr - i); - /* This function only handles jump-optimized kprobe */ - if (kp && kprobe_optimized(kp)) { - op = container_of(kp, struct optimized_kprobe, kp); - /* If op->list is not empty, op is under optimizing */ - if (list_empty(&op->list)) - goto found; - } - } - - return addr; -found: - /* - * If the kprobe can be optimized, original bytes which can be - * overwritten by jump destination address. In this case, original - * bytes must be recovered from op->optinsn.copied_insn buffer. - */ - memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - if (addr == (unsigned long)kp->addr) { - buf[0] = kp->opcode; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - } else { - offs = addr - (unsigned long)kp->addr - 1; - memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); - } - - return (unsigned long)buf; -} - -/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ -static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) -{ -#ifdef CONFIG_X86_64 - *addr++ = 0x48; - *addr++ = 0xbf; -#else - *addr++ = 0xb8; -#endif - *(unsigned long *)addr = val; -} - -static void __used __kprobes kprobes_optinsn_template_holder(void) -{ - asm volatile ( - ".global optprobe_template_entry\n" - "optprobe_template_entry:\n" -#ifdef CONFIG_X86_64 - /* We don't bother saving the ss register */ - " pushq %rsp\n" - " pushfq\n" - SAVE_REGS_STRING - " movq %rsp, %rsi\n" - ".global optprobe_template_val\n" - "optprobe_template_val:\n" - ASM_NOP5 - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call:\n" - ASM_NOP5 - /* Move flags to rsp */ - " movq 144(%rsp), %rdx\n" - " movq %rdx, 152(%rsp)\n" - RESTORE_REGS_STRING - /* Skip flags entry */ - " addq $8, %rsp\n" - " popfq\n" -#else /* CONFIG_X86_32 */ - " pushf\n" - SAVE_REGS_STRING - " movl %esp, %edx\n" - ".global optprobe_template_val\n" - "optprobe_template_val:\n" - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call:\n" - ASM_NOP5 - RESTORE_REGS_STRING - " addl $4, %esp\n" /* skip cs */ - " popf\n" -#endif - ".global optprobe_template_end\n" - "optprobe_template_end:\n"); -} - -#define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) -#define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) -#define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) - -#define INT3_SIZE sizeof(kprobe_opcode_t) - -/* Optimized kprobe call back function: called from optinsn */ -static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - - /* This is possible if op is under delayed unoptimizing */ - if (kprobe_disabled(&op->kp)) - return; - - local_irq_save(flags); - if (kprobe_running()) { - kprobes_inc_nmissed_count(&op->kp); - } else { - /* Save skipped registers */ -#ifdef CONFIG_X86_64 - regs->cs = __KERNEL_CS; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); - regs->gs = 0; -#endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; - regs->orig_ax = ~0UL; - - __this_cpu_write(current_kprobe, &op->kp); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - opt_pre_handler(&op->kp, regs); - __this_cpu_write(current_kprobe, NULL); - } - local_irq_restore(flags); -} - -static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) -{ - int len = 0, ret; - - while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len)) - return -EINVAL; - len += ret; - } - /* Check whether the address range is reserved */ - if (ftrace_text_reserved(src, src + len - 1) || - alternatives_text_reserved(src, src + len - 1) || - jump_label_text_reserved(src, src + len - 1)) - return -EBUSY; - - return len; -} - -/* Check whether insn is indirect jump */ -static int __kprobes insn_is_indirect_jump(struct insn *insn) -{ - return ((insn->opcode.bytes[0] == 0xff && - (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ - insn->opcode.bytes[0] == 0xea); /* Segment based jump */ -} - -/* Check whether insn jumps into specified address range */ -static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) -{ - unsigned long target = 0; - - switch (insn->opcode.bytes[0]) { - case 0xe0: /* loopne */ - case 0xe1: /* loope */ - case 0xe2: /* loop */ - case 0xe3: /* jcxz */ - case 0xe9: /* near relative jump */ - case 0xeb: /* short relative jump */ - break; - case 0x0f: - if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ - break; - return 0; - default: - if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ - break; - return 0; - } - target = (unsigned long)insn->next_byte + insn->immediate.value; - - return (start <= target && target <= start + len); -} - -/* Decode whole function to ensure any instructions don't jump into target */ -static int __kprobes can_optimize(unsigned long paddr) -{ - unsigned long addr, size = 0, offset = 0; - struct insn insn; - kprobe_opcode_t buf[MAX_INSN_SIZE]; - - /* Lookup symbol including addr */ - if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) - return 0; - - /* - * Do not optimize in the entry code due to the unstable - * stack handling. - */ - if ((paddr >= (unsigned long)__entry_text_start) && - (paddr < (unsigned long)__entry_text_end)) - return 0; - - /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) - return 0; - - /* Decode instructions */ - addr = paddr - offset; - while (addr < paddr - offset + size) { /* Decode until function end */ - if (search_exception_tables(addr)) - /* - * Since some fixup code will jumps into this function, - * we can't optimize kprobe in this function. - */ - return 0; - kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr)); - insn_get_length(&insn); - /* Another subsystem puts a breakpoint */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) - return 0; - /* Recover address */ - insn.kaddr = (void *)addr; - insn.next_byte = (void *)(addr + insn.length); - /* Check any instructions don't jump into target */ - if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) - return 0; - addr += insn.length; - } - - return 1; -} - -/* Check optimized_kprobe can actually be optimized. */ -int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) -{ - int i; - struct kprobe *p; - - for (i = 1; i < op->optinsn.size; i++) { - p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) - return -EEXIST; - } - - return 0; -} - -/* Check the addr is within the optimized instructions. */ -int __kprobes -arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) -{ - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + op->optinsn.size > addr); -} - -/* Free optimized instruction slot */ -static __kprobes -void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) -{ - if (op->optinsn.insn) { - free_optinsn_slot(op->optinsn.insn, dirty); - op->optinsn.insn = NULL; - op->optinsn.size = 0; - } -} - -void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) -{ - __arch_remove_optimized_kprobe(op, 1); -} - -/* - * Copy replacing target instructions - * Target instructions MUST be relocatable (checked inside) - * This is called when new aggr(opt)probe is allocated or reused. - */ -int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) -{ - u8 *buf; - int ret; - long rel; - - if (!can_optimize((unsigned long)op->kp.addr)) - return -EILSEQ; - - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) - return -ENOMEM; - - /* - * Verify if the address gap is in 2GB range, because this uses - * a relative jump. - */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; - if (abs(rel) > 0x7fffffff) - return -ERANGE; - - buf = (u8 *)op->optinsn.insn; - - /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } - op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); - - /* Set probe information */ - synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); - - /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); - - /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, - (u8 *)op->kp.addr + op->optinsn.size); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; -} - -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Replace breakpoints (int3) with relative jumps. - * Caller must call with locking kprobe_mutex and text_mutex. - */ -void __kprobes arch_optimize_kprobes(struct list_head *oplist) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - /* Set int3 to first byte for kprobes */ - insn_buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Recover original instructions and breakpoints from relative jumps. - * Caller must call with locking kprobe_mutex. - */ -extern void arch_unoptimize_kprobes(struct list_head *oplist, - struct list_head *done_list) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); -} - -int __kprobes -setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) -{ - struct optimized_kprobe *op; - - if (p->flags & KPROBE_FLAG_OPTIMIZED) { - /* This kprobe is really able to run optimized path. */ - op = container_of(p, struct optimized_kprobe, kp); - /* Detour through copied instructions */ - regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; - if (!reenter) - reset_current_kprobe(); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - -int __kprobes arch_init_optprobes(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c deleted file mode 100644 index 18114bfb10f3..000000000000 --- a/arch/x86/kernel/kprobes.c +++ /dev/null @@ -1,1064 +0,0 @@ -/* - * Kernel Probes (KProbes) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) IBM Corporation, 2002, 2004 - * - * 2002-Oct Created by Vamsi Krishna S Kernel - * Probes initial implementation ( includes contributions from - * Rusty Russell). - * 2004-July Suparna Bhattacharya added jumper probes - * interface to access function arguments. - * 2004-Oct Jim Keniston and Prasanna S Panchamukhi - * adapted for x86_64 from i386. - * 2005-Mar Roland McGrath - * Fixed to handle %rip-relative addressing mode correctly. - * 2005-May Hien Nguyen , Jim Keniston - * and Prasanna S Panchamukhi - * added function-return probes. - * 2005-May Rusty Lynch - * Added function return probes functionality - * 2006-Feb Masami Hiramatsu added - * kprobe-booster and kretprobe-booster for i386. - * 2007-Dec Masami Hiramatsu added kprobe-booster - * and kretprobe-booster for x86-64 - * 2007-Dec Masami Hiramatsu , Arjan van de Ven - * and Jim Keniston - * unified x86 kprobes code. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#include "kprobes-common.h" - -void jprobe_return_end(void); - -DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; -DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); - -#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs)) - -#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ - (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ - (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \ - (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) | \ - (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf)) \ - << (row % 32)) - /* - * Undefined/reserved opcodes, conditional jump, Opcode Extension - * Groups, and some special opcodes can not boost. - * This is non-const and volatile to keep gcc from statically - * optimizing it out, as variable_test_bit makes gcc think only - * *(unsigned long*) is used. - */ -static volatile u32 twobyte_is_boostable[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ---------------------------------------------- */ - W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */ - W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */ - W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */ - W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */ - W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */ - W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */ - W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */ - W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */ - W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */ - W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ - W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */ - W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */ - W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */ - W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */ - W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */ - W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0) /* f0 */ - /* ----------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; -#undef W - -struct kretprobe_blackpoint kretprobe_blacklist[] = { - {"__switch_to", }, /* This function switches only current task, but - doesn't switch kernel stack.*/ - {NULL, NULL} /* Terminator */ -}; - -const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); - -static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) -{ - struct __arch_relative_insn { - u8 op; - s32 raddr; - } __attribute__((packed)) *insn; - - insn = (struct __arch_relative_insn *)from; - insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); - insn->op = op; -} - -/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -void __kprobes synthesize_reljump(void *from, void *to) -{ - __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); -} - -/* Insert a call instruction at address 'from', which calls address 'to'.*/ -void __kprobes synthesize_relcall(void *from, void *to) -{ - __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); -} - -/* - * Skip the prefixes of the instruction. - */ -static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) -{ - insn_attr_t attr; - - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - while (inat_is_legacy_prefix(attr)) { - insn++; - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - } -#ifdef CONFIG_X86_64 - if (inat_is_rex_prefix(attr)) - insn++; -#endif - return insn; -} - -/* - * Returns non-zero if opcode is boostable. - * RIP relative instructions are adjusted at copying time in 64 bits mode - */ -int __kprobes can_boost(kprobe_opcode_t *opcodes) -{ - kprobe_opcode_t opcode; - kprobe_opcode_t *orig_opcodes = opcodes; - - if (search_exception_tables((unsigned long)opcodes)) - return 0; /* Page fault may occur on this address. */ - -retry: - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - opcode = *(opcodes++); - - /* 2nd-byte opcode */ - if (opcode == 0x0f) { - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - return test_bit(*opcodes, - (unsigned long *)twobyte_is_boostable); - } - - switch (opcode & 0xf0) { -#ifdef CONFIG_X86_64 - case 0x40: - goto retry; /* REX prefix is boostable */ -#endif - case 0x60: - if (0x63 < opcode && opcode < 0x67) - goto retry; /* prefixes */ - /* can't boost Address-size override and bound */ - return (opcode != 0x62 && opcode != 0x67); - case 0x70: - return 0; /* can't boost conditional jump */ - case 0xc0: - /* can't boost software-interruptions */ - return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf; - case 0xd0: - /* can boost AA* and XLAT */ - return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7); - case 0xe0: - /* can boost in/out and absolute jmps */ - return ((opcode & 0x04) || opcode == 0xea); - case 0xf0: - if ((opcode & 0x0c) == 0 && opcode != 0xf1) - goto retry; /* lock/rep(ne) prefix */ - /* clear and set flags are boostable */ - return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); - default: - /* segment override prefixes are boostable */ - if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e) - goto retry; /* prefixes */ - /* CS override prefix and call are not boostable */ - return (opcode != 0x2e && opcode != 0x9a); - } -} - -static unsigned long -__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) -{ - struct kprobe *kp; - - kp = get_kprobe((void *)addr); - /* There is no probe, return original address */ - if (!kp) - return addr; - - /* - * Basically, kp->ainsn.insn has an original instruction. - * However, RIP-relative instruction can not do single-stepping - * at different place, __copy_instruction() tweaks the displacement of - * that instruction. In that case, we can't recover the instruction - * from the kp->ainsn.insn. - * - * On the other hand, kp->opcode has a copy of the first byte of - * the probed instruction, which is overwritten by int3. And - * the instruction at kp->addr is not modified by kprobes except - * for the first byte, we can recover the original instruction - * from it and kp->opcode. - */ - memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - buf[0] = kp->opcode; - return (unsigned long)buf; -} - -/* - * Recover the probed instruction at addr for further analysis. - * Caller must lock kprobes by kprobe_mutex, or disable preemption - * for preventing to release referencing kprobes. - */ -unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) -{ - unsigned long __addr; - - __addr = __recover_optprobed_insn(buf, addr); - if (__addr != addr) - return __addr; - - return __recover_probed_insn(buf, addr); -} - -/* Check if paddr is at an instruction boundary */ -static int __kprobes can_probe(unsigned long paddr) -{ - unsigned long addr, __addr, offset = 0; - struct insn insn; - kprobe_opcode_t buf[MAX_INSN_SIZE]; - - if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) - return 0; - - /* Decode instructions */ - addr = paddr - offset; - while (addr < paddr) { - /* - * Check if the instruction has been modified by another - * kprobe, in which case we replace the breakpoint by the - * original instruction in our buffer. - * Also, jump optimization will change the breakpoint to - * relative-jump. Since the relative-jump itself is - * normally used, we just go through if there is no kprobe. - */ - __addr = recover_probed_instruction(buf, addr); - kernel_insn_init(&insn, (void *)__addr); - insn_get_length(&insn); - - /* - * Another debugging subsystem might insert this breakpoint. - * In that case, we can't recover it. - */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) - return 0; - addr += insn.length; - } - - return (addr == paddr); -} - -/* - * Returns non-zero if opcode modifies the interrupt flag. - */ -static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) -{ - /* Skip prefixes */ - insn = skip_prefixes(insn); - - switch (*insn) { - case 0xfa: /* cli */ - case 0xfb: /* sti */ - case 0xcf: /* iret/iretd */ - case 0x9d: /* popf/popfd */ - return 1; - } - - return 0; -} - -/* - * Copy an instruction and adjust the displacement if the instruction - * uses the %rip-relative addressing mode. - * If it does, Return the address of the 32-bit displacement word. - * If not, return null. - * Only applicable to 64-bit x86. - */ -int __kprobes __copy_instruction(u8 *dest, u8 *src) -{ - struct insn insn; - kprobe_opcode_t buf[MAX_INSN_SIZE]; - - kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); - insn_get_length(&insn); - /* Another subsystem puts a breakpoint, failed to recover */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) - return 0; - memcpy(dest, insn.kaddr, insn.length); - -#ifdef CONFIG_X86_64 - if (insn_rip_relative(&insn)) { - s64 newdisp; - u8 *disp; - kernel_insn_init(&insn, dest); - insn_get_displacement(&insn); - /* - * The copied instruction uses the %rip-relative addressing - * mode. Adjust the displacement for the difference between - * the original location of this instruction and the location - * of the copy that will actually be run. The tricky bit here - * is making sure that the sign extension happens correctly in - * this calculation, since we need a signed 32-bit result to - * be sign-extended to 64 bits when it's added to the %rip - * value and yield the same 64-bit result that the sign- - * extension of the original signed 32-bit displacement would - * have given. - */ - newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; - BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ - disp = (u8 *) dest + insn_offset_displacement(&insn); - *(s32 *) disp = (s32) newdisp; - } -#endif - return insn.length; -} - -static void __kprobes arch_copy_kprobe(struct kprobe *p) -{ - /* Copy an instruction with recovering if other optprobe modifies it.*/ - __copy_instruction(p->ainsn.insn, p->addr); - - /* - * __copy_instruction can modify the displacement of the instruction, - * but it doesn't affect boostable check. - */ - if (can_boost(p->ainsn.insn)) - p->ainsn.boostable = 0; - else - p->ainsn.boostable = -1; - - /* Also, displacement change doesn't affect the first byte */ - p->opcode = p->ainsn.insn[0]; -} - -int __kprobes arch_prepare_kprobe(struct kprobe *p) -{ - if (alternatives_text_reserved(p->addr, p->addr)) - return -EINVAL; - - if (!can_probe((unsigned long)p->addr)) - return -EILSEQ; - /* insn: must be on special executable page on x86. */ - p->ainsn.insn = get_insn_slot(); - if (!p->ainsn.insn) - return -ENOMEM; - arch_copy_kprobe(p); - return 0; -} - -void __kprobes arch_arm_kprobe(struct kprobe *p) -{ - text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); -} - -void __kprobes arch_disarm_kprobe(struct kprobe *p) -{ - text_poke(p->addr, &p->opcode, 1); -} - -void __kprobes arch_remove_kprobe(struct kprobe *p) -{ - if (p->ainsn.insn) { - free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); - p->ainsn.insn = NULL; - } -} - -static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) -{ - kcb->prev_kprobe.kp = kprobe_running(); - kcb->prev_kprobe.status = kcb->kprobe_status; - kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags; - kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags; -} - -static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) -{ - __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); - kcb->kprobe_status = kcb->prev_kprobe.status; - kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags; - kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; -} - -static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - __this_cpu_write(current_kprobe, p); - kcb->kprobe_saved_flags = kcb->kprobe_old_flags - = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - if (is_IF_modifier(p->ainsn.insn)) - kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; -} - -static void __kprobes clear_btf(void) -{ - if (test_thread_flag(TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - } -} - -static void __kprobes restore_btf(void) -{ - if (test_thread_flag(TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - } -} - -void __kprobes -arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) -{ - unsigned long *sara = stack_addr(regs); - - ri->ret_addr = (kprobe_opcode_t *) *sara; - - /* Replace the return addr with trampoline addr */ - *sara = (unsigned long) &kretprobe_trampoline; -} - -static void __kprobes -setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) -{ - if (setup_detour_execution(p, regs, reenter)) - return; - -#if !defined(CONFIG_PREEMPT) - if (p->ainsn.boostable == 1 && !p->post_handler) { - /* Boost up -- we can execute copied instructions directly */ - if (!reenter) - reset_current_kprobe(); - /* - * Reentering boosted probe doesn't reset current_kprobe, - * nor set current_kprobe, because it doesn't use single - * stepping. - */ - regs->ip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); - return; - } -#endif - if (reenter) { - save_previous_kprobe(kcb); - set_current_kprobe(p, regs, kcb); - kcb->kprobe_status = KPROBE_REENTER; - } else - kcb->kprobe_status = KPROBE_HIT_SS; - /* Prepare real single stepping */ - clear_btf(); - regs->flags |= X86_EFLAGS_TF; - regs->flags &= ~X86_EFLAGS_IF; - /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) - regs->ip = (unsigned long)p->addr; - else - regs->ip = (unsigned long)p->ainsn.insn; -} - -/* - * We have reentered the kprobe_handler(), since another probe was hit while - * within the handler. We save the original kprobes variables and just single - * step on the instruction of the new probe without calling any user handlers. - */ -static int __kprobes -reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) -{ - switch (kcb->kprobe_status) { - case KPROBE_HIT_SSDONE: - case KPROBE_HIT_ACTIVE: - kprobes_inc_nmissed_count(p); - setup_singlestep(p, regs, kcb, 1); - break; - case KPROBE_HIT_SS: - /* A probe has been hit in the codepath leading up to, or just - * after, single-stepping of a probed instruction. This entire - * codepath should strictly reside in .kprobes.text section. - * Raise a BUG or we'll continue in an endless reentering loop - * and eventually a stack overflow. - */ - printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", - p->addr); - dump_kprobe(p); - BUG(); - default: - /* impossible cases */ - WARN_ON(1); - return 0; - } - - return 1; -} - -/* - * Interrupts are disabled on entry as trap3 is an interrupt gate and they - * remain disabled throughout this function. - */ -static int __kprobes kprobe_handler(struct pt_regs *regs) -{ - kprobe_opcode_t *addr; - struct kprobe *p; - struct kprobe_ctlblk *kcb; - - addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); - /* - * We don't want to be preempted for the entire - * duration of kprobe processing. We conditionally - * re-enable preemption at the end of this function, - * and also in reenter_kprobe() and setup_singlestep(). - */ - preempt_disable(); - - kcb = get_kprobe_ctlblk(); - p = get_kprobe(addr); - - if (p) { - if (kprobe_running()) { - if (reenter_kprobe(p, regs, kcb)) - return 1; - } else { - set_current_kprobe(p, regs, kcb); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - - /* - * If we have no pre-handler or it returned 0, we - * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. - */ - if (!p->pre_handler || !p->pre_handler(p, regs)) - setup_singlestep(p, regs, kcb, 0); - return 1; - } - } else if (*addr != BREAKPOINT_INSTRUCTION) { - /* - * The breakpoint instruction was removed right - * after we hit it. Another cpu has removed - * either a probepoint or a debugger breakpoint - * at this address. In either case, no further - * handling of this interrupt is appropriate. - * Back up over the (now missing) int3 and run - * the original instruction. - */ - regs->ip = (unsigned long)addr; - preempt_enable_no_resched(); - return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - setup_singlestep(p, regs, kcb, 0); - return 1; - } - } /* else: not a kprobe fault; let the kernel handle it */ - - preempt_enable_no_resched(); - return 0; -} - -/* - * When a retprobed function returns, this code saves registers and - * calls trampoline_handler() runs, which calls the kretprobe's handler. - */ -static void __used __kprobes kretprobe_trampoline_holder(void) -{ - asm volatile ( - ".global kretprobe_trampoline\n" - "kretprobe_trampoline: \n" -#ifdef CONFIG_X86_64 - /* We don't bother saving the ss register */ - " pushq %rsp\n" - " pushfq\n" - SAVE_REGS_STRING - " movq %rsp, %rdi\n" - " call trampoline_handler\n" - /* Replace saved sp with true return address. */ - " movq %rax, 152(%rsp)\n" - RESTORE_REGS_STRING - " popfq\n" -#else - " pushf\n" - SAVE_REGS_STRING - " movl %esp, %eax\n" - " call trampoline_handler\n" - /* Move flags to cs */ - " movl 56(%esp), %edx\n" - " movl %edx, 52(%esp)\n" - /* Replace saved flags with true return address. */ - " movl %eax, 56(%esp)\n" - RESTORE_REGS_STRING - " popf\n" -#endif - " ret\n"); -} - -/* - * Called from kretprobe_trampoline - */ -static __used __kprobes void *trampoline_handler(struct pt_regs *regs) -{ - struct kretprobe_instance *ri = NULL; - struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; - kprobe_opcode_t *correct_ret_addr = NULL; - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); - /* fixup registers */ -#ifdef CONFIG_X86_64 - regs->cs = __KERNEL_CS; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); - regs->gs = 0; -#endif - regs->ip = trampoline_address; - regs->orig_ax = ~0UL; - - /* - * It is possible to have multiple instances associated with a given - * task either because multiple functions in the call path have - * return probes installed on them, and/or more than one - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always pushed into the head of the list - * - when multiple return probes are registered for the same - * function, the (chronologically) first instance's ret_addr - * will be the real return address, and all the rest will - * point to kretprobe_trampoline. - */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - kretprobe_assert(ri, orig_ret_address, trampoline_address); - - correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - if (ri->rp && ri->rp->handler) { - __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; - ri->ret_addr = correct_ret_addr; - ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); - } - - recycle_rp_inst(ri, &empty_rp); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - kretprobe_hash_unlock(current, &flags); - - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } - return (void *)orig_ret_address; -} - -/* - * Called after single-stepping. p->addr is the address of the - * instruction whose first byte has been replaced by the "int 3" - * instruction. To avoid the SMP problems that can occur when we - * temporarily put back the original opcode to single-step, we - * single-stepped a copy of the instruction. The address of this - * copy is p->ainsn.insn. - * - * This function prepares to return from the post-single-step - * interrupt. We have to fix up the stack as follows: - * - * 0) Except in the case of absolute or indirect jump or call instructions, - * the new ip is relative to the copied instruction. We need to make - * it relative to the original instruction. - * - * 1) If the single-stepped instruction was pushfl, then the TF and IF - * flags are set in the just-pushed flags, and may need to be cleared. - * - * 2) If the single-stepped instruction was a call, the return address - * that is atop the stack is the address following the copied instruction. - * We need to make it the address following the original instruction. - * - * If this is the first time we've single-stepped the instruction at - * this probepoint, and the instruction is boostable, boost it: add a - * jump instruction after the copied instruction, that jumps to the next - * instruction after the probepoint. - */ -static void __kprobes -resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) -{ - unsigned long *tos = stack_addr(regs); - unsigned long copy_ip = (unsigned long)p->ainsn.insn; - unsigned long orig_ip = (unsigned long)p->addr; - kprobe_opcode_t *insn = p->ainsn.insn; - - /* Skip prefixes */ - insn = skip_prefixes(insn); - - regs->flags &= ~X86_EFLAGS_TF; - switch (*insn) { - case 0x9c: /* pushfl */ - *tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF); - *tos |= kcb->kprobe_old_flags; - break; - case 0xc2: /* iret/ret/lret */ - case 0xc3: - case 0xca: - case 0xcb: - case 0xcf: - case 0xea: /* jmp absolute -- ip is correct */ - /* ip is already adjusted, no more changes required */ - p->ainsn.boostable = 1; - goto no_change; - case 0xe8: /* call relative - Fix return addr */ - *tos = orig_ip + (*tos - copy_ip); - break; -#ifdef CONFIG_X86_32 - case 0x9a: /* call absolute -- same as call absolute, indirect */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; -#endif - case 0xff: - if ((insn[1] & 0x30) == 0x10) { - /* - * call absolute, indirect - * Fix return addr; ip is correct. - * But this is not boostable - */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; - } else if (((insn[1] & 0x31) == 0x20) || - ((insn[1] & 0x31) == 0x21)) { - /* - * jmp near and far, absolute indirect - * ip is correct. And this is boostable - */ - p->ainsn.boostable = 1; - goto no_change; - } - default: - break; - } - - if (p->ainsn.boostable == 0) { - if ((regs->ip > copy_ip) && - (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) { - /* - * These instructions can be executed directly if it - * jumps back to correct address. - */ - synthesize_reljump((void *)regs->ip, - (void *)orig_ip + (regs->ip - copy_ip)); - p->ainsn.boostable = 1; - } else { - p->ainsn.boostable = -1; - } - } - - regs->ip += orig_ip - copy_ip; - -no_change: - restore_btf(); -} - -/* - * Interrupts are disabled on entry as trap1 is an interrupt gate and they - * remain disabled throughout this function. - */ -static int __kprobes post_kprobe_handler(struct pt_regs *regs) -{ - struct kprobe *cur = kprobe_running(); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (!cur) - return 0; - - resume_execution(cur, regs, kcb); - regs->flags |= kcb->kprobe_saved_flags; - - if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - cur->post_handler(cur, regs, 0); - } - - /* Restore back the original saved kprobes variables and continue. */ - if (kcb->kprobe_status == KPROBE_REENTER) { - restore_previous_kprobe(kcb); - goto out; - } - reset_current_kprobe(); -out: - preempt_enable_no_resched(); - - /* - * if somebody else is singlestepping across a probe point, flags - * will have TF set, in which case, continue the remaining processing - * of do_debug, as if this is not a probe hit. - */ - if (regs->flags & X86_EFLAGS_TF) - return 0; - - return 1; -} - -int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) -{ - struct kprobe *cur = kprobe_running(); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - switch (kcb->kprobe_status) { - case KPROBE_HIT_SS: - case KPROBE_REENTER: - /* - * We are here because the instruction being single - * stepped caused a page fault. We reset the current - * kprobe and the ip points back to the probe address - * and allow the page fault handler to continue as a - * normal page fault. - */ - regs->ip = (unsigned long)cur->addr; - regs->flags |= kcb->kprobe_old_flags; - if (kcb->kprobe_status == KPROBE_REENTER) - restore_previous_kprobe(kcb); - else - reset_current_kprobe(); - preempt_enable_no_resched(); - break; - case KPROBE_HIT_ACTIVE: - case KPROBE_HIT_SSDONE: - /* - * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accounting - * these specific fault cases. - */ - kprobes_inc_nmissed_count(cur); - - /* - * We come here because instructions in the pre/post - * handler caused the page_fault, this could happen - * if handler tries to access user space by - * copy_from_user(), get_user() etc. Let the - * user-specified handler try to fix it first. - */ - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - /* - * In case the user-specified fault handler returned - * zero, try to fix up. - */ - if (fixup_exception(regs)) - return 1; - - /* - * fixup routine could not handle it, - * Let do_page_fault() fix it. - */ - break; - default: - break; - } - return 0; -} - -/* - * Wrapper routine for handling exceptions. - */ -int __kprobes -kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) -{ - struct die_args *args = data; - int ret = NOTIFY_DONE; - - if (args->regs && user_mode_vm(args->regs)) - return ret; - - switch (val) { - case DIE_INT3: - if (kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_DEBUG: - if (post_kprobe_handler(args->regs)) { - /* - * Reset the BS bit in dr6 (pointed by args->err) to - * denote completion of processing - */ - (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; - ret = NOTIFY_STOP; - } - break; - case DIE_GPF: - /* - * To be potentially processing a kprobe fault and to - * trust the result from kprobe_running(), we have - * be non-preemptible. - */ - if (!preemptible() && kprobe_running() && - kprobe_fault_handler(args->regs, args->trapnr)) - ret = NOTIFY_STOP; - break; - default: - break; - } - return ret; -} - -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = stack_addr(regs); - addr = (unsigned long)(kcb->jprobe_saved_sp); - - /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - */ - memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, - MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); - regs->ip = (unsigned long)(jp->entry); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - asm volatile ( -#ifdef CONFIG_X86_64 - " xchg %%rbx,%%rsp \n" -#else - " xchgl %%ebx,%%esp \n" -#endif - " int3 \n" - " .globl jprobe_return_end\n" - " jprobe_return_end: \n" - " nop \n"::"b" - (kcb->jprobe_saved_sp):"memory"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - u8 *addr = (u8 *) (regs->ip - 1); - struct jprobe *jp = container_of(p, struct jprobe, kp); - - if ((addr > (u8 *) jprobe_return) && - (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { - struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; - printk(KERN_ERR - "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); - printk(KERN_ERR "Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk(KERN_ERR "Current registers\n"); - show_regs(regs); - BUG(); - } - *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - -int __init arch_init_kprobes(void) -{ - return arch_init_optprobes(); -} - -int __kprobes arch_trampoline_kprobe(struct kprobe *p) -{ - return 0; -} diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile new file mode 100644 index 000000000000..0d33169cc1a2 --- /dev/null +++ b/arch/x86/kernel/kprobes/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for kernel probes +# + +obj-$(CONFIG_KPROBES) += core.o +obj-$(CONFIG_OPTPROBES) += opt.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h new file mode 100644 index 000000000000..2e9d4b5af036 --- /dev/null +++ b/arch/x86/kernel/kprobes/common.h @@ -0,0 +1,113 @@ +#ifndef __X86_KERNEL_KPROBES_COMMON_H +#define __X86_KERNEL_KPROBES_COMMON_H + +/* Kprobes and Optprobes common header */ + +#ifdef CONFIG_X86_64 +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $16, %esp\n" \ + " pushl %fs\n" \ + " pushl %es\n" \ + " pushl %ds\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ + " addl $24, %esp\n" +#endif + +/* Ensure if the instruction can be boostable */ +extern int can_boost(kprobe_opcode_t *instruction); +/* Recover instruction if given address is probed */ +extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, + unsigned long addr); +/* + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. + */ +extern int __copy_instruction(u8 *dest, u8 *src); + +/* Generate a relative-jump/call instruction */ +extern void synthesize_reljump(void *from, void *to); +extern void synthesize_relcall(void *from, void *to); + +#ifdef CONFIG_OPTPROBES +extern int arch_init_optprobes(void); +extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); +extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); +#else /* !CONFIG_OPTPROBES */ +static inline int arch_init_optprobes(void) +{ + return 0; +} +static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + return 0; +} +static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + return addr; +} +#endif + +#ifdef CONFIG_KPROBES_ON_FTRACE +extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb); +#else +static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + return 0; +} +#endif +#endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c new file mode 100644 index 000000000000..e124554598ee --- /dev/null +++ b/arch/x86/kernel/kprobes/core.c @@ -0,0 +1,1064 @@ +/* + * Kernel Probes (KProbes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * 2002-Oct Created by Vamsi Krishna S Kernel + * Probes initial implementation ( includes contributions from + * Rusty Russell). + * 2004-July Suparna Bhattacharya added jumper probes + * interface to access function arguments. + * 2004-Oct Jim Keniston and Prasanna S Panchamukhi + * adapted for x86_64 from i386. + * 2005-Mar Roland McGrath + * Fixed to handle %rip-relative addressing mode correctly. + * 2005-May Hien Nguyen , Jim Keniston + * and Prasanna S Panchamukhi + * added function-return probes. + * 2005-May Rusty Lynch + * Added function return probes functionality + * 2006-Feb Masami Hiramatsu added + * kprobe-booster and kretprobe-booster for i386. + * 2007-Dec Masami Hiramatsu added kprobe-booster + * and kretprobe-booster for x86-64 + * 2007-Dec Masami Hiramatsu , Arjan van de Ven + * and Jim Keniston + * unified x86 kprobes code. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "common.h" + +void jprobe_return_end(void); + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs)) + +#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ + (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ + (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \ + (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) | \ + (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf)) \ + << (row % 32)) + /* + * Undefined/reserved opcodes, conditional jump, Opcode Extension + * Groups, and some special opcodes can not boost. + * This is non-const and volatile to keep gcc from statically + * optimizing it out, as variable_test_bit makes gcc think only + * *(unsigned long*) is used. + */ +static volatile u32 twobyte_is_boostable[256 / 32] = { + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* ---------------------------------------------- */ + W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */ + W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */ + W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */ + W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */ + W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */ + W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */ + W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */ + W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */ + W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */ + W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ + W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */ + W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */ + W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */ + W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */ + W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */ + W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0) /* f0 */ + /* ----------------------------------------------- */ + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ +}; +#undef W + +struct kretprobe_blackpoint kretprobe_blacklist[] = { + {"__switch_to", }, /* This function switches only current task, but + doesn't switch kernel stack.*/ + {NULL, NULL} /* Terminator */ +}; + +const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); + +static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) +{ + struct __arch_relative_insn { + u8 op; + s32 raddr; + } __packed *insn; + + insn = (struct __arch_relative_insn *)from; + insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); + insn->op = op; +} + +/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ +void __kprobes synthesize_reljump(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); +} + +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +void __kprobes synthesize_relcall(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); +} + +/* + * Skip the prefixes of the instruction. + */ +static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) +{ + insn_attr_t attr; + + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + while (inat_is_legacy_prefix(attr)) { + insn++; + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + } +#ifdef CONFIG_X86_64 + if (inat_is_rex_prefix(attr)) + insn++; +#endif + return insn; +} + +/* + * Returns non-zero if opcode is boostable. + * RIP relative instructions are adjusted at copying time in 64 bits mode + */ +int __kprobes can_boost(kprobe_opcode_t *opcodes) +{ + kprobe_opcode_t opcode; + kprobe_opcode_t *orig_opcodes = opcodes; + + if (search_exception_tables((unsigned long)opcodes)) + return 0; /* Page fault may occur on this address. */ + +retry: + if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) + return 0; + opcode = *(opcodes++); + + /* 2nd-byte opcode */ + if (opcode == 0x0f) { + if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) + return 0; + return test_bit(*opcodes, + (unsigned long *)twobyte_is_boostable); + } + + switch (opcode & 0xf0) { +#ifdef CONFIG_X86_64 + case 0x40: + goto retry; /* REX prefix is boostable */ +#endif + case 0x60: + if (0x63 < opcode && opcode < 0x67) + goto retry; /* prefixes */ + /* can't boost Address-size override and bound */ + return (opcode != 0x62 && opcode != 0x67); + case 0x70: + return 0; /* can't boost conditional jump */ + case 0xc0: + /* can't boost software-interruptions */ + return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf; + case 0xd0: + /* can boost AA* and XLAT */ + return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7); + case 0xe0: + /* can boost in/out and absolute jmps */ + return ((opcode & 0x04) || opcode == 0xea); + case 0xf0: + if ((opcode & 0x0c) == 0 && opcode != 0xf1) + goto retry; /* lock/rep(ne) prefix */ + /* clear and set flags are boostable */ + return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); + default: + /* segment override prefixes are boostable */ + if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e) + goto retry; /* prefixes */ + /* CS override prefix and call are not boostable */ + return (opcode != 0x2e && opcode != 0x9a); + } +} + +static unsigned long +__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct kprobe *kp; + + kp = get_kprobe((void *)addr); + /* There is no probe, return original address */ + if (!kp) + return addr; + + /* + * Basically, kp->ainsn.insn has an original instruction. + * However, RIP-relative instruction can not do single-stepping + * at different place, __copy_instruction() tweaks the displacement of + * that instruction. In that case, we can't recover the instruction + * from the kp->ainsn.insn. + * + * On the other hand, kp->opcode has a copy of the first byte of + * the probed instruction, which is overwritten by int3. And + * the instruction at kp->addr is not modified by kprobes except + * for the first byte, we can recover the original instruction + * from it and kp->opcode. + */ + memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + buf[0] = kp->opcode; + return (unsigned long)buf; +} + +/* + * Recover the probed instruction at addr for further analysis. + * Caller must lock kprobes by kprobe_mutex, or disable preemption + * for preventing to release referencing kprobes. + */ +unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + unsigned long __addr; + + __addr = __recover_optprobed_insn(buf, addr); + if (__addr != addr) + return __addr; + + return __recover_probed_insn(buf, addr); +} + +/* Check if paddr is at an instruction boundary */ +static int __kprobes can_probe(unsigned long paddr) +{ + unsigned long addr, __addr, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + /* + * Check if the instruction has been modified by another + * kprobe, in which case we replace the breakpoint by the + * original instruction in our buffer. + * Also, jump optimization will change the breakpoint to + * relative-jump. Since the relative-jump itself is + * normally used, we just go through if there is no kprobe. + */ + __addr = recover_probed_instruction(buf, addr); + kernel_insn_init(&insn, (void *)__addr); + insn_get_length(&insn); + + /* + * Another debugging subsystem might insert this breakpoint. + * In that case, we can't recover it. + */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; + addr += insn.length; + } + + return (addr == paddr); +} + +/* + * Returns non-zero if opcode modifies the interrupt flag. + */ +static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) +{ + /* Skip prefixes */ + insn = skip_prefixes(insn); + + switch (*insn) { + case 0xfa: /* cli */ + case 0xfb: /* sti */ + case 0xcf: /* iret/iretd */ + case 0x9d: /* popf/popfd */ + return 1; + } + + return 0; +} + +/* + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. + * If it does, Return the address of the 32-bit displacement word. + * If not, return null. + * Only applicable to 64-bit x86. + */ +int __kprobes __copy_instruction(u8 *dest, u8 *src) +{ + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); + insn_get_length(&insn); + /* Another subsystem puts a breakpoint, failed to recover */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; + memcpy(dest, insn.kaddr, insn.length); + +#ifdef CONFIG_X86_64 + if (insn_rip_relative(&insn)) { + s64 newdisp; + u8 *disp; + kernel_insn_init(&insn, dest); + insn_get_displacement(&insn); + /* + * The copied instruction uses the %rip-relative addressing + * mode. Adjust the displacement for the difference between + * the original location of this instruction and the location + * of the copy that will actually be run. The tricky bit here + * is making sure that the sign extension happens correctly in + * this calculation, since we need a signed 32-bit result to + * be sign-extended to 64 bits when it's added to the %rip + * value and yield the same 64-bit result that the sign- + * extension of the original signed 32-bit displacement would + * have given. + */ + newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; + BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ + disp = (u8 *) dest + insn_offset_displacement(&insn); + *(s32 *) disp = (s32) newdisp; + } +#endif + return insn.length; +} + +static void __kprobes arch_copy_kprobe(struct kprobe *p) +{ + /* Copy an instruction with recovering if other optprobe modifies it.*/ + __copy_instruction(p->ainsn.insn, p->addr); + + /* + * __copy_instruction can modify the displacement of the instruction, + * but it doesn't affect boostable check. + */ + if (can_boost(p->ainsn.insn)) + p->ainsn.boostable = 0; + else + p->ainsn.boostable = -1; + + /* Also, displacement change doesn't affect the first byte */ + p->opcode = p->ainsn.insn[0]; +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + if (alternatives_text_reserved(p->addr, p->addr)) + return -EINVAL; + + if (!can_probe((unsigned long)p->addr)) + return -EILSEQ; + /* insn: must be on special executable page on x86. */ + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + arch_copy_kprobe(p); + return 0; +} + +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); +} + +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + text_poke(p->addr, &p->opcode, 1); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); + p->ainsn.insn = NULL; + } +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; + kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags; + kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags; + kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; +} + +static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, p); + kcb->kprobe_saved_flags = kcb->kprobe_old_flags + = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); + if (is_IF_modifier(p->ainsn.insn)) + kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; +} + +static void __kprobes clear_btf(void) +{ + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } +} + +static void __kprobes restore_btf(void) +{ + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl |= DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } +} + +void __kprobes +arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + unsigned long *sara = stack_addr(regs); + + ri->ret_addr = (kprobe_opcode_t *) *sara; + + /* Replace the return addr with trampoline addr */ + *sara = (unsigned long) &kretprobe_trampoline; +} + +static void __kprobes +setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) +{ + if (setup_detour_execution(p, regs, reenter)) + return; + +#if !defined(CONFIG_PREEMPT) + if (p->ainsn.boostable == 1 && !p->post_handler) { + /* Boost up -- we can execute copied instructions directly */ + if (!reenter) + reset_current_kprobe(); + /* + * Reentering boosted probe doesn't reset current_kprobe, + * nor set current_kprobe, because it doesn't use single + * stepping. + */ + regs->ip = (unsigned long)p->ainsn.insn; + preempt_enable_no_resched(); + return; + } +#endif + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_REENTER; + } else + kcb->kprobe_status = KPROBE_HIT_SS; + /* Prepare real single stepping */ + clear_btf(); + regs->flags |= X86_EFLAGS_TF; + regs->flags &= ~X86_EFLAGS_IF; + /* single step inline if the instruction is an int3 */ + if (p->opcode == BREAKPOINT_INSTRUCTION) + regs->ip = (unsigned long)p->addr; + else + regs->ip = (unsigned long)p->ainsn.insn; +} + +/* + * We have reentered the kprobe_handler(), since another probe was hit while + * within the handler. We save the original kprobes variables and just single + * step on the instruction of the new probe without calling any user handlers. + */ +static int __kprobes +reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + /* A probe has been hit in the codepath leading up to, or just + * after, single-stepping of a probed instruction. This entire + * codepath should strictly reside in .kprobes.text section. + * Raise a BUG or we'll continue in an endless reentering loop + * and eventually a stack overflow. + */ + printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", + p->addr); + dump_kprobe(p); + BUG(); + default: + /* impossible cases */ + WARN_ON(1); + return 0; + } + + return 1; +} + +/* + * Interrupts are disabled on entry as trap3 is an interrupt gate and they + * remain disabled throughout this function. + */ +static int __kprobes kprobe_handler(struct pt_regs *regs) +{ + kprobe_opcode_t *addr; + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); + /* + * We don't want to be preempted for the entire + * duration of kprobe processing. We conditionally + * re-enable preemption at the end of this function, + * and also in reenter_kprobe() and setup_singlestep(). + */ + preempt_disable(); + + kcb = get_kprobe_ctlblk(); + p = get_kprobe(addr); + + if (p) { + if (kprobe_running()) { + if (reenter_kprobe(p, regs, kcb)) + return 1; + } else { + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it prepped + * for calling the break_handler below on re-entry + * for jprobe processing, so get out doing nothing + * more here. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + return 1; + } + } else if (*addr != BREAKPOINT_INSTRUCTION) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Back up over the (now missing) int3 and run + * the original instruction. + */ + regs->ip = (unsigned long)addr; + preempt_enable_no_resched(); + return 1; + } else if (kprobe_running()) { + p = __this_cpu_read(current_kprobe); + if (p->break_handler && p->break_handler(p, regs)) { + if (!skip_singlestep(p, regs, kcb)) + setup_singlestep(p, regs, kcb, 0); + return 1; + } + } /* else: not a kprobe fault; let the kernel handle it */ + + preempt_enable_no_resched(); + return 0; +} + +/* + * When a retprobed function returns, this code saves registers and + * calls trampoline_handler() runs, which calls the kretprobe's handler. + */ +static void __used __kprobes kretprobe_trampoline_holder(void) +{ + asm volatile ( + ".global kretprobe_trampoline\n" + "kretprobe_trampoline: \n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rdi\n" + " call trampoline_handler\n" + /* Replace saved sp with true return address. */ + " movq %rax, 152(%rsp)\n" + RESTORE_REGS_STRING + " popfq\n" +#else + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %eax\n" + " call trampoline_handler\n" + /* Move flags to cs */ + " movl 56(%esp), %edx\n" + " movl %edx, 52(%esp)\n" + /* Replace saved flags with true return address. */ + " movl %eax, 56(%esp)\n" + RESTORE_REGS_STRING + " popf\n" +#endif + " ret\n"); +} + +/* + * Called from kretprobe_trampoline + */ +static __used __kprobes void *trampoline_handler(struct pt_regs *regs) +{ + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; + unsigned long flags, orig_ret_address = 0; + unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; + kprobe_opcode_t *correct_ret_addr = NULL; + + INIT_HLIST_HEAD(&empty_rp); + kretprobe_hash_lock(current, &head, &flags); + /* fixup registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = trampoline_address; + regs->orig_ax = ~0UL; + + /* + * It is possible to have multiple instances associated with a given + * task either because multiple functions in the call path have + * return probes installed on them, and/or more than one + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always pushed into the head of the list + * - when multiple return probes are registered for the same + * function, the (chronologically) first instance's ret_addr + * will be the real return address, and all the rest will + * point to kretprobe_trampoline. + */ + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + if (ri->rp && ri->rp->handler) { + __this_cpu_write(current_kprobe, &ri->rp->kp); + get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; + ri->ret_addr = correct_ret_addr; + ri->rp->handler(ri, regs); + __this_cpu_write(current_kprobe, NULL); + } + + recycle_rp_inst(ri, &empty_rp); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_hash_unlock(current, &flags); + + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + return (void *)orig_ret_address; +} + +/* + * Called after single-stepping. p->addr is the address of the + * instruction whose first byte has been replaced by the "int 3" + * instruction. To avoid the SMP problems that can occur when we + * temporarily put back the original opcode to single-step, we + * single-stepped a copy of the instruction. The address of this + * copy is p->ainsn.insn. + * + * This function prepares to return from the post-single-step + * interrupt. We have to fix up the stack as follows: + * + * 0) Except in the case of absolute or indirect jump or call instructions, + * the new ip is relative to the copied instruction. We need to make + * it relative to the original instruction. + * + * 1) If the single-stepped instruction was pushfl, then the TF and IF + * flags are set in the just-pushed flags, and may need to be cleared. + * + * 2) If the single-stepped instruction was a call, the return address + * that is atop the stack is the address following the copied instruction. + * We need to make it the address following the original instruction. + * + * If this is the first time we've single-stepped the instruction at + * this probepoint, and the instruction is boostable, boost it: add a + * jump instruction after the copied instruction, that jumps to the next + * instruction after the probepoint. + */ +static void __kprobes +resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +{ + unsigned long *tos = stack_addr(regs); + unsigned long copy_ip = (unsigned long)p->ainsn.insn; + unsigned long orig_ip = (unsigned long)p->addr; + kprobe_opcode_t *insn = p->ainsn.insn; + + /* Skip prefixes */ + insn = skip_prefixes(insn); + + regs->flags &= ~X86_EFLAGS_TF; + switch (*insn) { + case 0x9c: /* pushfl */ + *tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF); + *tos |= kcb->kprobe_old_flags; + break; + case 0xc2: /* iret/ret/lret */ + case 0xc3: + case 0xca: + case 0xcb: + case 0xcf: + case 0xea: /* jmp absolute -- ip is correct */ + /* ip is already adjusted, no more changes required */ + p->ainsn.boostable = 1; + goto no_change; + case 0xe8: /* call relative - Fix return addr */ + *tos = orig_ip + (*tos - copy_ip); + break; +#ifdef CONFIG_X86_32 + case 0x9a: /* call absolute -- same as call absolute, indirect */ + *tos = orig_ip + (*tos - copy_ip); + goto no_change; +#endif + case 0xff: + if ((insn[1] & 0x30) == 0x10) { + /* + * call absolute, indirect + * Fix return addr; ip is correct. + * But this is not boostable + */ + *tos = orig_ip + (*tos - copy_ip); + goto no_change; + } else if (((insn[1] & 0x31) == 0x20) || + ((insn[1] & 0x31) == 0x21)) { + /* + * jmp near and far, absolute indirect + * ip is correct. And this is boostable + */ + p->ainsn.boostable = 1; + goto no_change; + } + default: + break; + } + + if (p->ainsn.boostable == 0) { + if ((regs->ip > copy_ip) && + (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + synthesize_reljump((void *)regs->ip, + (void *)orig_ip + (regs->ip - copy_ip)); + p->ainsn.boostable = 1; + } else { + p->ainsn.boostable = -1; + } + } + + regs->ip += orig_ip - copy_ip; + +no_change: + restore_btf(); +} + +/* + * Interrupts are disabled on entry as trap1 is an interrupt gate and they + * remain disabled throughout this function. + */ +static int __kprobes post_kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (!cur) + return 0; + + resume_execution(cur, regs, kcb); + regs->flags |= kcb->kprobe_saved_flags; + + if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + cur->post_handler(cur, regs, 0); + } + + /* Restore back the original saved kprobes variables and continue. */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + goto out; + } + reset_current_kprobe(); +out: + preempt_enable_no_resched(); + + /* + * if somebody else is singlestepping across a probe point, flags + * will have TF set, in which case, continue the remaining processing + * of do_debug, as if this is not a probe hit. + */ + if (regs->flags & X86_EFLAGS_TF) + return 0; + + return 1; +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->ip = (unsigned long)cur->addr; + regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + + /* + * fixup routine could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; + } + return 0; +} + +/* + * Wrapper routine for handling exceptions. + */ +int __kprobes +kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) +{ + struct die_args *args = data; + int ret = NOTIFY_DONE; + + if (args->regs && user_mode_vm(args->regs)) + return ret; + + switch (val) { + case DIE_INT3: + if (kprobe_handler(args->regs)) + ret = NOTIFY_STOP; + break; + case DIE_DEBUG: + if (post_kprobe_handler(args->regs)) { + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; + ret = NOTIFY_STOP; + } + break; + case DIE_GPF: + /* + * To be potentially processing a kprobe fault and to + * trust the result from kprobe_running(), we have + * be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(args->regs, args->trapnr)) + ret = NOTIFY_STOP; + break; + default: + break; + } + return ret; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + unsigned long addr; + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + kcb->jprobe_saved_regs = *regs; + kcb->jprobe_saved_sp = stack_addr(regs); + addr = (unsigned long)(kcb->jprobe_saved_sp); + + /* + * As Linus pointed out, gcc assumes that the callee + * owns the argument space and could overwrite it, e.g. + * tailcall optimization. So, to be absolutely safe + * we also save and restore enough stack bytes to cover + * the argument area. + */ + memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, + MIN_STACK_SIZE(addr)); + regs->flags &= ~X86_EFLAGS_IF; + trace_hardirqs_off(); + regs->ip = (unsigned long)(jp->entry); + return 1; +} + +void __kprobes jprobe_return(void) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + asm volatile ( +#ifdef CONFIG_X86_64 + " xchg %%rbx,%%rsp \n" +#else + " xchgl %%ebx,%%esp \n" +#endif + " int3 \n" + " .globl jprobe_return_end\n" + " jprobe_return_end: \n" + " nop \n"::"b" + (kcb->jprobe_saved_sp):"memory"); +} + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + u8 *addr = (u8 *) (regs->ip - 1); + struct jprobe *jp = container_of(p, struct jprobe, kp); + + if ((addr > (u8 *) jprobe_return) && + (addr < (u8 *) jprobe_return_end)) { + if (stack_addr(regs) != kcb->jprobe_saved_sp) { + struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; + printk(KERN_ERR + "current sp %p does not match saved sp %p\n", + stack_addr(regs), kcb->jprobe_saved_sp); + printk(KERN_ERR "Saved registers for jprobe %p\n", jp); + show_regs(saved_regs); + printk(KERN_ERR "Current registers\n"); + show_regs(regs); + BUG(); + } + *regs = kcb->jprobe_saved_regs; + memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), + kcb->jprobes_stack, + MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + preempt_enable_no_resched(); + return 1; + } + return 0; +} + +int __init arch_init_kprobes(void) +{ + return arch_init_optprobes(); +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c new file mode 100644 index 000000000000..23ef5c556f06 --- /dev/null +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -0,0 +1,93 @@ +/* + * Dynamic Ftrace based Kprobes Optimization + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) Hitachi Ltd., 2012 + */ +#include +#include +#include +#include +#include + +#include "common.h" + +static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); + return 1; +} + +int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + if (kprobe_ftrace(p)) + return __skip_singlestep(p, regs, kcb); + else + return 0; +} + +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + __skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c new file mode 100644 index 000000000000..76dc6f095724 --- /dev/null +++ b/arch/x86/kernel/kprobes/opt.c @@ -0,0 +1,512 @@ +/* + * Kernel Probes Jump Optimization (Optprobes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * Copyright (C) Hitachi Ltd., 2012 + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "common.h" + +unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct optimized_kprobe *op; + struct kprobe *kp; + long offs; + int i; + + for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + kp = get_kprobe((void *)addr - i); + /* This function only handles jump-optimized kprobe */ + if (kp && kprobe_optimized(kp)) { + op = container_of(kp, struct optimized_kprobe, kp); + /* If op->list is not empty, op is under optimizing */ + if (list_empty(&op->list)) + goto found; + } + } + + return addr; +found: + /* + * If the kprobe can be optimized, original bytes which can be + * overwritten by jump destination address. In this case, original + * bytes must be recovered from op->optinsn.copied_insn buffer. + */ + memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (addr == (unsigned long)kp->addr) { + buf[0] = kp->opcode; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + } else { + offs = addr - (unsigned long)kp->addr - 1; + memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + } + + return (unsigned long)buf; +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +static void __used __kprobes kprobes_optinsn_template_holder(void) +{ + asm volatile ( + ".global optprobe_template_entry\n" + "optprobe_template_entry:\n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 144(%rsp), %rdx\n" + " movq %rdx, 152(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + RESTORE_REGS_STRING + " addl $4, %esp\n" /* skip cs */ + " popf\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end:\n"); +} + +#define TMPL_MOVE_IDX \ + ((long)&optprobe_template_val - (long)&optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)&optprobe_template_call - (long)&optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)&optprobe_template_end - (long)&optprobe_template_entry) + +#define INT3_SIZE sizeof(kprobe_opcode_t) + +/* Optimized kprobe call back function: called from optinsn */ +static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long flags; + + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + + local_irq_save(flags); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + /* Save skipped registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->orig_ax = ~0UL; + + __this_cpu_write(current_kprobe, &op->kp); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __this_cpu_write(current_kprobe, NULL); + } + local_irq_restore(flags); +} + +static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +{ + int len = 0, ret; + + while (len < RELATIVEJUMP_SIZE) { + ret = __copy_instruction(dest + len, src + len); + if (!ret || !can_boost(dest + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __kprobes insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int __kprobes can_optimize(unsigned long paddr) +{ + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) + return 0; + + /* + * Do not optimize in the entry code due to the unstable + * stack handling. + */ + if ((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < RELATIVEJUMP_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr)); + insn_get_length(&insn); + /* Another subsystem puts a breakpoint */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_SIZE, + RELATIVE_ADDR_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disabled(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int __kprobes +arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static __kprobes +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + if (op->optinsn.insn) { + free_optinsn_slot(op->optinsn.insn, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + * This is called when new aggr(opt)probe is allocated or reused. + */ +int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +{ + u8 *buf; + int ret; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + op->optinsn.insn = get_optinsn_slot(); + if (!op->optinsn.insn) + return -ENOMEM; + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + if (abs(rel) > 0x7fffffff) + return -ERANGE; + + buf = (u8 *)op->optinsn.insn; + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); + if (ret < 0) { + __arch_remove_optimized_kprobe(op, 0); + return ret; + } + op->optinsn.size = ret; + + /* Copy arch-dep-instance from template */ + memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + (u8 *)op->kp.addr + op->optinsn.size); + + flush_icache_range((unsigned long) buf, + (unsigned long) buf + TMPL_END_IDX + + op->optinsn.size + RELATIVEJUMP_SIZE); + return 0; +} + +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + u8 buf[RELATIVEJUMP_SIZE]; + + /* Set int3 to first byte for kprobes */ + buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); +} + +int __kprobes +setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + return 0; +} + +int __kprobes arch_init_optprobes(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} -- cgit v1.2.2 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 +++++---- 1 file changed, 5 insertions(+), 4 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(); -- cgit v1.2.2 From 444723dccc3c855fe88ea138cdec46f30e707b74 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 24 Jan 2013 09:27:31 +0000 Subject: x86-64: Fix unwind annotations in recent NMI changes While in one case a plain annotation is necessary, in the other case the stack adjustment can simply be folded into the immediately preceding RESTORE_ALL, thus getting the correct annotation for free. Signed-off-by: Jan Beulich Cc: Steven Rostedt Cc: Linus Torvalds Cc: Alexander van Heukelum Link: http://lkml.kernel.org/r/51010C9302000078000B9045@nat28.tlf.novell.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/entry_64.S | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 07a7a04529bc..cb3c591339aa 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1781,6 +1781,7 @@ first_nmi: * Leave room for the "copied" frame */ subq $(5*8), %rsp + CFI_ADJUST_CFA_OFFSET 5*8 /* Copy the stack frame to the Saved frame */ .rept 5 @@ -1863,10 +1864,8 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - RESTORE_ALL 8 - - /* Pop the extra iret frame */ - addq $(5*8), %rsp + /* Pop the extra iret frame at once */ + RESTORE_ALL 6*8 /* Clear the NMI executing stack variable */ movq $0, 5*8(%rsp) -- cgit v1.2.2 From e3f0f36ddf1b2743a0d4ea312996536a9c37e1c7 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 18 Jan 2013 12:58:47 -0500 Subject: x86/apic: Remove noisy zero-mask warning from default_send_IPI_mask_logical() Since circa 3.5, we've had dozens of reports of people hitting this warning. Forwarded reports have been met with silence, so just remove the warning if no-one cares. Example reports: https://bugzilla.redhat.com/show_bug.cgi?id=797687 https://bugzilla.redhat.com/show_bug.cgi?id=867174 https://bugzilla.redhat.com/show_bug.cgi?id=894865 Signed-off-by: Dave Jones Cc: Andrew Morton Link: http://lkml.kernel.org/r/20130118175847.GA27662@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/ipi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index cce91bf26676..7434d8556d09 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -106,7 +106,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) unsigned long mask = cpumask_bits(cpumask)[0]; unsigned long flags; - if (WARN_ONCE(!mask, "empty IPI mask")) + if (!mask) return; local_irq_save(flags); -- cgit v1.2.2 From b9975dabe3f0a6e4d1af52c47f66b5558df207a3 Mon Sep 17 00:00:00 2001 From: Cong Ding Date: Mon, 14 Jan 2013 22:39:18 +0100 Subject: x86/apb/timer: Remove unnecessary "if" adev has no chance to be NULL, so we don't need to check it. It is also dereferenced just before the check . Signed-off-by: Cong Ding Cc: Sasha Levin Link: http://lkml.kernel.org/r/1358199561-15518-1-git-send-email-dinggnu@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apb_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index afdc3f756dea..cf9273571917 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -240,7 +240,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n, dw_apb_clockevent_pause(adev->timer); if (system_state == SYSTEM_RUNNING) { pr_debug("skipping APBT CPU %lu offline\n", cpu); - } else if (adev) { + } else { pr_debug("APBT clockevent for cpu %lu offline\n", cpu); dw_apb_clockevent_stop(adev->timer); } -- cgit v1.2.2 From 4cca6ea04d31c22a7d0436949c072b27bde41f86 Mon Sep 17 00:00:00 2001 From: Alok N Kataria Date: Thu, 17 Jan 2013 15:44:42 -0800 Subject: x86/apic: Allow x2apic without IR on VMware platform This patch updates x2apic initializaition code to allow x2apic on VMware platform even without interrupt remapping support. The hypervisor_x2apic_available hook was added in x2apic initialization code and used by KVM and XEN, before this. I have also cleaned up that code to export this hook through the hypervisor_x86 structure. Compile tested for KVM and XEN configs, this patch doesn't have any functional effect on those two platforms. On VMware platform, verified that x2apic is used in physical mode on products that support this. Signed-off-by: Alok N Kataria Reviewed-by: Doug Covelli Reviewed-by: Dan Hecht Acked-by: H. Peter Anvin Cc: Konrad Rzeszutek Wilk Cc: Jeremy Fitzhardinge Cc: Avi Kivity Link: http://lkml.kernel.org/r/1358466282.423.60.camel@akataria-dtop.eng.vmware.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/hypervisor.c | 7 +++++++ arch/x86/kernel/cpu/vmware.c | 13 +++++++++++++ arch/x86/kernel/kvm.c | 1 + 3 files changed, 21 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index a8f8fa9769d6..1e7e84a02eba 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -79,3 +79,10 @@ void __init init_hypervisor_platform(void) if (x86_hyper->init_platform) x86_hyper->init_platform(); } + +bool __init hypervisor_x2apic_available(void) +{ + return x86_hyper && + x86_hyper->x2apic_available && + x86_hyper->x2apic_available(); +} diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d22d0c4edcfd..03a36321ec54 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -33,6 +33,9 @@ #define VMWARE_PORT_CMD_GETVERSION 10 #define VMWARE_PORT_CMD_GETHZ 45 +#define VMWARE_PORT_CMD_GETVCPU_INFO 68 +#define VMWARE_PORT_CMD_LEGACY_X2APIC 3 +#define VMWARE_PORT_CMD_VCPU_RESERVED 31 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ __asm__("inl (%%dx)" : \ @@ -125,10 +128,20 @@ static void __cpuinit vmware_set_cpu_features(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); } +/* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */ +static bool __init vmware_legacy_x2apic_available(void) +{ + uint32_t eax, ebx, ecx, edx; + VMWARE_PORT(GETVCPU_INFO, eax, ebx, ecx, edx); + return (eax & (1 << VMWARE_PORT_CMD_VCPU_RESERVED)) == 0 && + (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; +} + const __refconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, .set_cpu_features = vmware_set_cpu_features, .init_platform = vmware_platform_setup, + .x2apic_available = vmware_legacy_x2apic_available, }; EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9c2bd8bd4b4c..2b44ea5f269d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -505,6 +505,7 @@ static bool __init kvm_detect(void) const struct hypervisor_x86 x86_hyper_kvm __refconst = { .name = "KVM", .detect = kvm_detect, + .x2apic_available = kvm_para_available, }; EXPORT_SYMBOL_GPL(x86_hyper_kvm); -- cgit v1.2.2 From 6125bc8b86d9da75ddac77e38f41afbf9f5de3e3 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 4 Jan 2013 15:41:47 -0700 Subject: x86/time/rtc: Don't print extended CMOS year when reading RTC We shouldn't print the current century every time we read the RTC. Signed-off-by: Bjorn Helgaas Acked-by: Thomas Gleixner Link: http://lkml.kernel.org/r/20130104224146.15189.14874.stgit@bhelgaas.mtv.corp.google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/rtc.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 801602b5d745..2e8f3d3b5641 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -149,7 +149,6 @@ unsigned long mach_get_cmos_time(void) if (century) { century = bcd2bin(century); year += century * 100; - printk(KERN_INFO "Extended CMOS year: %d\n", century * 100); } else year += CMOS_YEARS_OFFS; -- cgit v1.2.2 From 0927b482ae69acb7605f6be1ad3860b657512fbd Mon Sep 17 00:00:00 2001 From: ShuoX Liu Date: Sat, 29 Dec 2012 00:48:44 +0800 Subject: perf/x86: Enable Intel Lincroft/Penwell/Cloverview Atom support These three chip are based on Atom and have different model id. So add such three id for perf HW event support. Signed-off-by: ShuoX Liu Cc: yanmin_zhang@intel.linux.com Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1356713324-12442-1-git-send-email-shuox.liu@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 93b9e1181f83..cb313a56c21b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2019,7 +2019,10 @@ __init int intel_pmu_init(void) break; case 28: /* Atom */ - case 54: /* Cedariew */ + case 38: /* Lincroft */ + case 39: /* Penwell */ + case 53: /* Cloverview */ + case 54: /* Cedarview */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); -- cgit v1.2.2 From 9faec5be3a27f95ee359b42c6c81b3173eb13958 Mon Sep 17 00:00:00 2001 From: yangyongqiang Date: Tue, 18 Dec 2012 12:22:25 -0800 Subject: perf/x86: Fix P6 driver section warning Fix a compile warning - 'a section type conflict' by removing __initconst. Signed-off-by: yangyongqiang Cc: Cyrill Gorcunov Cc: Vince Weaver Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_p6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index f2af39f5dc3d..4820c232a0b9 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] = }; -static __initconst u64 p6_hw_cache_event_ids +static u64 p6_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = -- cgit v1.2.2 From 923d8697e24847000490c187de1aeaca622611a3 Mon Sep 17 00:00:00 2001 From: Youquan Song Date: Tue, 18 Dec 2012 12:20:23 -0500 Subject: x86/perf: Add IvyBridge EP support Running the perf utility on a Ivybridge EP server we encounter "not supported" events: L1-dcache-loads L1-dcache-load-misses L1-dcache-stores L1-dcache-store-misses L1-dcache-prefetches L1-dcache-prefetch-misses This patch adds support for this processor. Signed-off-by: Youquan Song Cc: Andi Kleen Cc: Youquan Song Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1355851223-27705-1-git-send-email-youquan.song@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cb313a56c21b..4914e94ad6e8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2087,6 +2087,7 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; case 58: /* IvyBridge */ + case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, -- cgit v1.2.2 From e3e81aca8d51a50e19d6c67fafc4c9c4f0404bf1 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Mon, 17 Dec 2012 17:42:56 +0800 Subject: x86: Fix a typo legact -> legacy Signed-off-by: Yuanhan Liu Signed-off-by: Ingo Molnar --- arch/x86/kernel/sys_x86_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 97ef74b88e0f..dbded5aedb81 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -157,7 +157,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (flags & MAP_FIXED) return addr; - /* for MAP_32BIT mappings we force the legact mmap base */ + /* for MAP_32BIT mappings we force the legacy mmap base */ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) goto bottomup; -- cgit v1.2.2 From 9611dc7a8de8a5c6244886dad020995b1a896236 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 23 Nov 2012 16:33:05 +0000 Subject: x86: Convert a few mistaken __cpuinit annotations to __init The first two are functions serving as initcalls; the SFI one is only being called from __init code. Signed-off-by: Jan Beulich Link: http://lkml.kernel.org/r/50AFB35102000078000AAECA@nat28.tlf.novell.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_cacheinfo.c | 2 +- 1 file changed, 1 insertion(+), 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 fe9edec6698a..0e462404d6f1 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -1227,7 +1227,7 @@ static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = { .notifier_call = cacheinfo_cpu_callback, }; -static int __cpuinit cache_sysfs_init(void) +static int __init cache_sysfs_init(void) { int i; -- cgit v1.2.2 From 51906e779f2b13b38f8153774c4c7163d412ffd9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 19 Nov 2012 16:01:29 +0100 Subject: x86/MSI: Support multiple MSIs in presense of IRQ remapping The MSI specification has several constraints in comparison with MSI-X, most notable of them is the inability to configure MSIs independently. As a result, it is impossible to dispatch interrupts from different queues to different CPUs. This is largely devalues the support of multiple MSIs in SMP systems. Also, a necessity to allocate a contiguous block of vector numbers for devices capable of multiple MSIs might cause a considerable pressure on x86 interrupt vector allocator and could lead to fragmentation of the interrupt vectors space. This patch overcomes both drawbacks in presense of IRQ remapping and lets devices take advantage of multiple queues and per-IRQ affinity assignments. Signed-off-by: Alexander Gordeev Cc: Bjorn Helgaas Cc: Suresh Siddha Cc: Yinghai Lu Cc: Matthew Wilcox Cc: Jeff Garzik Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/c8bd86ff56b5fc118257436768aaa04489ac0a4c.1353324359.git.agordeev@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/io_apic.c | 165 +++++++++++++++++++++++++++++++++-------- 1 file changed, 133 insertions(+), 32 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 b739d398bb29..2016f9dabd72 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -300,9 +300,9 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irq_from(unsigned int from, int node) +static int alloc_irqs_from(unsigned int from, unsigned int count, int node) { - return irq_alloc_desc_from(from, node); + return irq_alloc_descs_from(from, count, node); } static void free_irq_at(unsigned int at, struct irq_cfg *cfg) @@ -2982,37 +2982,58 @@ device_initcall(ioapic_init_ops); /* * Dynamic irq allocate and deallocation */ -unsigned int create_irq_nr(unsigned int from, int node) +unsigned int __create_irqs(unsigned int from, unsigned int count, int node) { - struct irq_cfg *cfg; + struct irq_cfg **cfg; unsigned long flags; - unsigned int ret = 0; - int irq; + int irq, i; if (from < nr_irqs_gsi) from = nr_irqs_gsi; - irq = alloc_irq_from(from, node); - if (irq < 0) - return 0; - cfg = alloc_irq_cfg(irq, node); - if (!cfg) { - free_irq_at(irq, NULL); + cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node); + if (!cfg) return 0; + + irq = alloc_irqs_from(from, count, node); + if (irq < 0) + goto out_cfgs; + + for (i = 0; i < count; i++) { + cfg[i] = alloc_irq_cfg(irq + i, node); + if (!cfg[i]) + goto out_irqs; } raw_spin_lock_irqsave(&vector_lock, flags); - if (!__assign_irq_vector(irq, cfg, apic->target_cpus())) - ret = irq; + for (i = 0; i < count; i++) + if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus())) + goto out_vecs; raw_spin_unlock_irqrestore(&vector_lock, flags); - if (ret) { - irq_set_chip_data(irq, cfg); - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } else { - free_irq_at(irq, cfg); + for (i = 0; i < count; i++) { + irq_set_chip_data(irq + i, cfg[i]); + irq_clear_status_flags(irq + i, IRQ_NOREQUEST); } - return ret; + + kfree(cfg); + return irq; + +out_vecs: + for (i--; i >= 0; i--) + __clear_irq_vector(irq + i, cfg[i]); + raw_spin_unlock_irqrestore(&vector_lock, flags); +out_irqs: + for (i = 0; i < count; i++) + free_irq_at(irq + i, cfg[i]); +out_cfgs: + kfree(cfg); + return 0; +} + +unsigned int create_irq_nr(unsigned int from, int node) +{ + return __create_irqs(from, 1, node); } int create_irq(void) @@ -3045,6 +3066,14 @@ void destroy_irq(unsigned int irq) free_irq_at(irq, cfg); } +static inline void destroy_irqs(unsigned int irq, unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) + destroy_irq(irq + i); +} + /* * MSI message composition */ @@ -3071,7 +3100,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, if (irq_remapped(cfg)) { compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); - return err; + return 0; } if (x2apic_enabled()) @@ -3098,7 +3127,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, MSI_DATA_DELIVERY_LOWPRI) | MSI_DATA_VECTOR(cfg->vector); - return err; + return 0; } static int @@ -3136,18 +3165,26 @@ static struct irq_chip msi_chip = { .irq_retrigger = ioapic_retrigger_irq, }; -static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) +static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset) { struct irq_chip *chip = &msi_chip; struct msi_msg msg; + unsigned int irq = irq_base + irq_offset; int ret; ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; - irq_set_msi_desc(irq, msidesc); - write_msi_msg(irq, &msg); + irq_set_msi_desc_off(irq_base, irq_offset, msidesc); + + /* + * MSI-X message is written per-IRQ, the offset is always 0. + * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. + */ + if (!irq_offset) + write_msi_msg(irq, &msg); if (irq_remapped(irq_get_chip_data(irq))) { irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); @@ -3161,23 +3198,19 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) return 0; } -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +int setup_msix_irqs(struct pci_dev *dev, int nvec) { int node, ret, sub_handle, index = 0; unsigned int irq, irq_want; struct msi_desc *msidesc; - /* x86 doesn't support multiple MSI yet */ - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - node = dev_to_node(&dev->dev); irq_want = nr_irqs_gsi; sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { irq = create_irq_nr(irq_want, node); if (irq == 0) - return -1; + return -ENOSPC; irq_want = irq + 1; if (!irq_remapping_enabled) goto no_ir; @@ -3199,7 +3232,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) goto error; } no_ir: - ret = setup_msi_irq(dev, msidesc, irq); + ret = setup_msi_irq(dev, msidesc, irq, 0); if (ret < 0) goto error; sub_handle++; @@ -3211,6 +3244,74 @@ error: return ret; } +int setup_msi_irqs(struct pci_dev *dev, int nvec) +{ + int node, ret, sub_handle, index = 0; + unsigned int irq; + struct msi_desc *msidesc; + + if (nvec > 1 && !irq_remapping_enabled) + return 1; + + nvec = __roundup_pow_of_two(nvec); + + WARN_ON(!list_is_singular(&dev->msi_list)); + msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + WARN_ON(msidesc->irq); + WARN_ON(msidesc->msi_attrib.multiple); + + node = dev_to_node(&dev->dev); + irq = __create_irqs(nr_irqs_gsi, nvec, node); + if (irq == 0) + return -ENOSPC; + + if (!irq_remapping_enabled) { + ret = setup_msi_irq(dev, msidesc, irq, 0); + if (ret < 0) + goto error; + return 0; + } + + msidesc->msi_attrib.multiple = ilog2(nvec); + for (sub_handle = 0; sub_handle < nvec; sub_handle++) { + if (!sub_handle) { + index = msi_alloc_remapped_irq(dev, irq, nvec); + if (index < 0) { + ret = index; + goto error; + } + } else { + ret = msi_setup_remapped_irq(dev, irq + sub_handle, + index, sub_handle); + if (ret < 0) + goto error; + } + ret = setup_msi_irq(dev, msidesc, irq, sub_handle); + if (ret < 0) + goto error; + } + return 0; + +error: + destroy_irqs(irq, nvec); + + /* + * Restore altered MSI descriptor fields and prevent just destroyed + * IRQs from tearing down again in default_teardown_msi_irqs() + */ + msidesc->irq = 0; + msidesc->msi_attrib.multiple = 0; + + return ret; +} + +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + if (type == PCI_CAP_ID_MSI) + return setup_msi_irqs(dev, nvec); + return setup_msix_irqs(dev, nvec); +} + void native_teardown_msi_irq(unsigned int irq) { destroy_irq(irq); -- cgit v1.2.2 From 73b664ceb5f815c38def1c68912b83f83455e9eb Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Fri, 16 Nov 2012 11:17:14 +0100 Subject: x86/dma-debug: Bump PREALLOC_DMA_DEBUG_ENTRIES I ran out of free entries when I had CONFIG_DMA_API_DEBUG enabled. Some other archs seem to default to 65536, so increase this limit for x86 too. Signed-off-by: Maarten Lankhorst Cc: Bjorn Helgaas Link: http://lkml.kernel.org/r/50A612AA.7040206@canonical.com Signed-off-by: Ingo Molnar ---- --- arch/x86/kernel/pci-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 0f5dec5c80e0..872079a67e4d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -56,7 +56,7 @@ struct device x86_dma_fallback_dev = { EXPORT_SYMBOL(x86_dma_fallback_dev); /* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES 32768 +#define PREALLOC_DMA_DEBUG_ENTRIES 65536 int dma_set_mask(struct device *dev, u64 mask) { -- cgit v1.2.2 From c903f0456bc69176912dee6dd25c6a66ee1aed00 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 15 Nov 2012 13:06:22 +0000 Subject: x86/msr: Add capabilities check At the moment the MSR driver only relies upon file system checks. This means that anything as root with any capability set can write to MSRs. Historically that wasn't very interesting but on modern processors the MSRs are such that writing to them provides several ways to execute arbitary code in kernel space. Sample code and documentation on doing this is circulating and MSR attacks are used on Windows 64bit rootkits already. In the Linux case you still need to be able to open the device file so the impact is fairly limited and reduces the security of some capability and security model based systems down towards that of a generic "root owns the box" setup. Therefore they should require CAP_SYS_RAWIO to prevent an elevation of capabilities. The impact of this is fairly minimal on most setups because they don't have heavy use of capabilities. Those using SELinux, SMACK or AppArmor rules might want to consider if their rulesets on the MSR driver could be tighter. Signed-off-by: Alan Cox Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Horses Signed-off-by: Ingo Molnar --- arch/x86/kernel/msr.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index a7c5661f8496..4929502c1372 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file) unsigned int cpu; struct cpuinfo_x86 *c; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ -- cgit v1.2.2 From 349eab6eb07794c59e37703ccbfeb5920721885c Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Tue, 6 Nov 2012 14:45:46 +0800 Subject: x86/process: Change %8s to %s for pr_warn() in release_thread() the length of dead_task->comm[] is 16 (TASK_COMM_LEN) on pr_warn(), it is not meaningful to use %8s for task->comm[]. So change it to %s, since the line is not solid anyway. Additional information: %8s limit the width, not for the original string output length if name length is more than 8, it still can be fully displayed. if name length is less than 8, the ' ' will be filled before name. %.8s truly limit the original string output length (precision) Signed-off-by: Chen Gang Link: http://lkml.kernel.org/n/tip-nridm1zvreai1tgfLjuexDmd@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6e68a6194965..0f49677da51e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -117,7 +117,7 @@ void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { if (dead_task->mm->context.size) { - pr_warn("WARNING: dead process %8s still has LDT? <%p/%d>\n", + pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, dead_task->mm->context.size); -- cgit v1.2.2 From 43720bd6014327ac454434496cb953edcdb9f8d6 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 11 Jan 2013 13:43:45 +0100 Subject: PM / tracing: remove deprecated power trace API The text in Documentation said it would be removed in 2.6.41; the text in the Kconfig said removal in the 3.1 release. Either way you look at it, we are well past both, so push it off a cliff. Note that the POWER_CSTATE and the POWER_PSTATE are part of the legacy tracing API. Remove all tracepoints which use these flags. As can be seen from context, most already have a trace entry via trace_cpu_idle anyways. Also, the cpufreq/cpufreq.c PSTATE one is actually unpaired, as compared to the CSTATE ones which all have a clear start/stop. As part of this, the trace_power_frequency also becomes orphaned, so it too is deleted. Signed-off-by: Paul Gortmaker Acked-by: Steven Rostedt Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/process.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2ed787f15bf0..dcfc1f410dc4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -375,7 +375,6 @@ void cpu_idle(void) */ void default_idle(void) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); trace_cpu_idle_rcuidle(1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* @@ -389,7 +388,6 @@ void default_idle(void) 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()); } #ifdef CONFIG_APM_MODULE @@ -423,7 +421,6 @@ void stop_this_cpu(void *dummy) static void mwait_idle(void) { if (!need_resched()) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -434,7 +431,6 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_power_end_rcuidle(smp_processor_id()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else local_irq_enable(); @@ -447,12 +443,10 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id()); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end_rcuidle(smp_processor_id()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } -- cgit v1.2.2 From 5dfd486c4750c9278c63fa96e6e85bdd2fb58e9d Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 22 Jan 2013 13:24:35 -0800 Subject: x86, kvm: Fix kvm's use of __pa() on percpu areas In short, it is illegal to call __pa() on an address holding a percpu variable. This replaces those __pa() calls with slow_virt_to_phys(). All of the cases in this patch are in boot time (or CPU hotplug time at worst) code, so the slow pagetable walking in slow_virt_to_phys() is not expected to have a performance impact. The times when this actually matters are pretty obscure (certain 32-bit NUMA systems), but it _does_ happen. It is important to keep KVM guests working on these systems because the real hardware is getting harder and harder to find. This bug manifested first by me seeing a plain hang at boot after this message: CPU 0 irqstacks, hard=f3018000 soft=f301a000 or, sometimes, it would actually make it out to the console: [ 0.000000] BUG: unable to handle kernel paging request at ffffffff I eventually traced it down to the KVM async pagefault code. This can be worked around by disabling that code either at compile-time, or on the kernel command-line. The kvm async pagefault code was injecting page faults in to the guest which the guest misinterpreted because its "reason" was not being properly sent from the host. The guest passes a physical address of an per-cpu async page fault structure via an MSR to the host. Since __pa() is broken on percpu data, the physical address it sent was bascially bogus and the host went scribbling on random data. The guest never saw the real reason for the page fault (it was injected by the host), assumed that the kernel had taken a _real_ page fault, and panic()'d. The behavior varied, though, depending on what got corrupted by the bad write. Signed-off-by: Dave Hansen Link: http://lkml.kernel.org/r/20130122212435.4905663F@kernel.stglabs.ibm.com Acked-by: Rik van Riel Reviewed-by: Marcelo Tosatti Signed-off-by: H. Peter Anvin --- arch/x86/kernel/kvm.c | 9 +++++---- arch/x86/kernel/kvmclock.c | 4 ++-- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9c2bd8bd4b4c..aa7e58b82b39 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -297,9 +297,9 @@ static void kvm_register_steal_time(void) memset(st, 0, sizeof(*st)); - wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED)); + wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED)); printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n", - cpu, __pa(st)); + cpu, slow_virt_to_phys(st)); } static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; @@ -324,7 +324,7 @@ void __cpuinit kvm_guest_cpu_init(void) return; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = __pa(&__get_cpu_var(apf_reason)); + u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason)); #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; @@ -340,7 +340,8 @@ void __cpuinit kvm_guest_cpu_init(void) /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); __get_cpu_var(kvm_apic_eoi) = 0; - pa = __pa(&__get_cpu_var(kvm_apic_eoi)) | KVM_MSR_ENABLED; + pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi)) + | KVM_MSR_ENABLED; wrmsrl(MSR_KVM_PV_EOI_EN, pa); } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 220a360010f8..9f966dc0b9e4 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -162,8 +162,8 @@ int kvm_register_clock(char *txt) int low, high, ret; struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti; - low = (int)__pa(src) | 1; - high = ((u64)__pa(src) >> 32); + low = (int)slow_virt_to_phys(src) | 1; + high = ((u64)slow_virt_to_phys(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); -- cgit v1.2.2 From 6fac4829ce0ef9b7f24369086ce5f0e9f38d37bc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 13 Nov 2012 14:20:55 +0100 Subject: cputime: Use accessors to read task cputime stats This is in preparation for the full dynticks feature. While remotely reading the cputime of a task running in a full dynticks CPU, we'll need to do some extra-computation. This way we can account the time it spent tickless in userspace since its last cputime snapshot. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- arch/x86/kernel/apm_32.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index d65464e43503..8d7012b7f402 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -899,6 +899,7 @@ static void apm_cpu_idle(void) static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ static unsigned int last_stime; /* = 0 */ + cputime_t stime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -906,23 +907,23 @@ static void apm_cpu_idle(void) WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: + task_cputime(current, NULL, &stime); if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = current->stime - last_stime; + idle_percentage = stime - last_stime; idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); if (apm_info.forbid_idle) use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } + last_jiffies = jiffies; + last_stime = stime; + bucket = IDLE_LEAKY_MAX; while (!need_resched()) { -- cgit v1.2.2 From 70733e0c7ed22177e2cfe660fa2a0e90f1f39126 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:33 +0200 Subject: x86, apic: Move irq_remapping_enabled checks into IRQ-remapping code Move the three easy to move checks in the x86' apic.c file into the IRQ-remapping code. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/apic.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b994cc84aa7e..8d741e65ff64 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1477,8 +1477,7 @@ void __init bsp_end_local_APIC_setup(void) * Now that local APIC setup is completed for BP, configure the fault * handling for interrupt remapping. */ - if (irq_remapping_enabled) - irq_remap_enable_fault_handling(); + irq_remap_enable_fault_handling(); } @@ -2251,8 +2250,7 @@ static int lapic_suspend(void) local_irq_save(flags); disable_local_APIC(); - if (irq_remapping_enabled) - irq_remapping_disable(); + irq_remapping_disable(); local_irq_restore(flags); return 0; @@ -2320,8 +2318,7 @@ static void lapic_resume(void) apic_write(APIC_ESR, 0); apic_read(APIC_ESR); - if (irq_remapping_enabled) - irq_remapping_reenable(x2apic_mode); + irq_remapping_reenable(x2apic_mode); local_irq_restore(flags); } -- cgit v1.2.2 From 336224ba5e4fb42a95d02ab0aa0fdff21649bb38 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:34 +0200 Subject: x86, apic: Mask IO-APIC and PIC unconditionally on LAPIC resume IO-APIC and PIC use the same resume routines when IRQ remapping is enabled or disabled. So it should be safe to mask the other APICs for the IRQ-remapping-disabled case too. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/apic.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8d741e65ff64..a5b4dce1b7ac 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2266,16 +2266,15 @@ static void lapic_resume(void) return; local_irq_save(flags); - if (irq_remapping_enabled) { - /* - * IO-APIC and PIC have their own resume routines. - * We just mask them here to make sure the interrupt - * subsystem is completely quiet while we enable x2apic - * and interrupt-remapping. - */ - mask_ioapic_entries(); - legacy_pic->mask_all(); - } + + /* + * IO-APIC and PIC have their own resume routines. + * We just mask them here to make sure the interrupt + * subsystem is completely quiet while we enable x2apic + * and interrupt-remapping. + */ + mask_ioapic_entries(); + legacy_pic->mask_all(); if (x2apic_mode) enable_x2apic(); -- cgit v1.2.2 From 1c4248ca4e783e47cc34e313d9f82b4ea52774cc Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:35 +0200 Subject: x86, io_apic: Introduce x86_io_apic_ops.disable() This function pointer is used to call a system-specific function for disabling the IO-APIC. Currently this is used for IRQ remapping which has its own disable routine. Also introduce the necessary infrastructure in the interrupt remapping code to overwrite this and other function pointers as necessary by interrupt remapping. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 41 +++++++++++++++++++---------------------- arch/x86/kernel/x86_init.c | 9 +++++---- 2 files changed, 24 insertions(+), 26 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 2016f9dabd72..cd5f4d7cc163 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1921,30 +1921,14 @@ void __init enable_IO_APIC(void) clear_IO_APIC(); } -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) +void native_disable_io_apic(void) { - /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - - if (!legacy_pic->nr_legacy_irqs) - return; - /* * If the i8259 is routed through an IOAPIC * Put that IOAPIC in virtual wire mode * so legacy interrupts can be delivered. - * - * With interrupt-remapping, for now we will use virtual wire A mode, - * as virtual wire B is little complex (need to configure both - * IOAPIC RTE as well as interrupt-remapping table entry). - * As this gets called during crash dump, keep this simple for now. */ - if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) { + if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); @@ -1964,12 +1948,25 @@ void disable_IO_APIC(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } + if (cpu_has_apic || apic_from_smp_config()) + disconnect_bsp_APIC(ioapic_i8259.pin != -1); + +} + +/* + * Not an __init, needed by the reboot code + */ +void disable_IO_APIC(void) +{ /* - * Use virtual wire A mode when interrupt remapping is enabled. + * Clear the IO-APIC before rebooting: */ - if (cpu_has_apic || apic_from_smp_config()) - disconnect_bsp_APIC(!irq_remapping_enabled && - ioapic_i8259.pin != -1); + clear_IO_APIC(); + + if (!legacy_pic->nr_legacy_irqs) + return; + + x86_io_apic_ops.disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 7a3d075a814a..754524acc845 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -118,8 +118,9 @@ struct x86_msi_ops x86_msi = { }; struct x86_io_apic_ops x86_io_apic_ops = { - .init = native_io_apic_init_mappings, - .read = native_io_apic_read, - .write = native_io_apic_write, - .modify = native_io_apic_modify, + .init = native_io_apic_init_mappings, + .read = native_io_apic_read, + .write = native_io_apic_write, + .modify = native_io_apic_modify, + .disable = native_disable_io_apic, }; -- cgit v1.2.2 From afcc8a40a090f7a65d3b72bac1a26fc6dbb63b10 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:36 +0200 Subject: x86, io_apic: Introduce x86_io_apic_ops.print_entries for debugging This call-back is used to dump IO-APIC entries for debugging purposes into the kernel log. VT-d needs a special routine for this and will overwrite the default. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 109 +++++++++++++++++++++-------------------- arch/x86/kernel/x86_init.c | 1 + 2 files changed, 57 insertions(+), 53 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 cd5f4d7cc163..a18e27a8882a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1513,9 +1513,63 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, ioapic_write_entry(ioapic_idx, pin, entry); } -__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) +{ + int i; + + pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + pr_debug(" %02x %02X ", i, entry.dest); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector); + } +} + +void intel_ir_io_apic_print_entries(unsigned int apic, + unsigned int nr_entries) { int i; + + pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IR_IO_APIC_route_entry *ir_entry; + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + ir_entry = (struct IR_IO_APIC_route_entry *)&entry; + + pr_debug(" %02x %04X ", i, ir_entry->index); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %X %02X\n", + ir_entry->format, + ir_entry->mask, + ir_entry->trigger, + ir_entry->irr, + ir_entry->polarity, + ir_entry->delivery_status, + ir_entry->index2, + ir_entry->zero, + ir_entry->vector); + } +} + +__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +{ union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; union IO_APIC_reg_02 reg_02; @@ -1568,58 +1622,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) printk(KERN_DEBUG ".... IRQ redirection table:\n"); - if (irq_remapping_enabled) { - printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR" - " Pol Stat Indx2 Zero Vect:\n"); - } else { - printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect:\n"); - } - - for (i = 0; i <= reg_01.bits.entries; i++) { - if (irq_remapping_enabled) { - struct IO_APIC_route_entry entry; - struct IR_IO_APIC_route_entry *ir_entry; - - entry = ioapic_read_entry(ioapic_idx, i); - ir_entry = (struct IR_IO_APIC_route_entry *) &entry; - printk(KERN_DEBUG " %02x %04X ", - i, - ir_entry->index - ); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector - ); - } else { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(ioapic_idx, i); - printk(KERN_DEBUG " %02x %02X ", - i, - entry.dest - ); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); - } - } + x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); } __apicdebuginit(void) print_IO_APICs(void) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 754524acc845..ee4af8b04841 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -123,4 +123,5 @@ struct x86_io_apic_ops x86_io_apic_ops = { .write = native_io_apic_write, .modify = native_io_apic_modify, .disable = native_disable_io_apic, + .print_entries = native_io_apic_print_entries, }; -- cgit v1.2.2 From 71054d8841b442bb3d8be60bde2bfac0483c19da Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:37 +0200 Subject: x86, hpet: Introduce x86_msi_ops.setup_hpet_msi This function pointer can be overwritten by the IRQ remapping code. The irq_remapping_enabled check can be removed from default_setup_hpet_msi. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 8 +------- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/x86_init.c | 10 ++++++---- 3 files changed, 8 insertions(+), 12 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 a18e27a8882a..e7b87630c13d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3399,18 +3399,12 @@ static struct irq_chip hpet_msi_type = { .irq_retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq, unsigned int id) +int default_setup_hpet_msi(unsigned int irq, unsigned int id) { struct irq_chip *chip = &hpet_msi_type; struct msi_msg msg; int ret; - if (irq_remapping_enabled) { - ret = setup_hpet_msi_remapped(irq, id); - if (ret) - return ret; - } - ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index e28670f9a589..da85a8e830a1 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -478,7 +478,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq, hpet_blockid)) { + if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ee4af8b04841..0357eee65673 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -111,10 +112,11 @@ struct x86_platform_ops x86_platform = { EXPORT_SYMBOL_GPL(x86_platform); struct x86_msi_ops x86_msi = { - .setup_msi_irqs = native_setup_msi_irqs, - .teardown_msi_irq = native_teardown_msi_irq, - .teardown_msi_irqs = default_teardown_msi_irqs, - .restore_msi_irqs = default_restore_msi_irqs, + .setup_msi_irqs = native_setup_msi_irqs, + .teardown_msi_irq = native_teardown_msi_irq, + .teardown_msi_irqs = default_teardown_msi_irqs, + .restore_msi_irqs = default_restore_msi_irqs, + .setup_hpet_msi = default_setup_hpet_msi, }; struct x86_io_apic_ops x86_io_apic_ops = { -- cgit v1.2.2 From 5afba62cc8a16716508605e02c1b02ee5f969184 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:38 +0200 Subject: x86, msi: Use IRQ remapping specific setup_msi_irqs routine Use seperate routines to setup MSI IRQs for both irq_remapping_enabled cases. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 104 ++++------------------------------------- 1 file changed, 10 insertions(+), 94 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 e7b87630c13d..d4b045e018fb 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3066,7 +3066,7 @@ void destroy_irq(unsigned int irq) free_irq_at(irq, cfg); } -static inline void destroy_irqs(unsigned int irq, unsigned int count) +void destroy_irqs(unsigned int irq, unsigned int count) { unsigned int i; @@ -3165,8 +3165,8 @@ static struct irq_chip msi_chip = { .irq_retrigger = ioapic_retrigger_irq, }; -static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset) +int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset) { struct irq_chip *chip = &msi_chip; struct msi_msg msg; @@ -3198,44 +3198,28 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, return 0; } -int setup_msix_irqs(struct pci_dev *dev, int nvec) +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int node, ret, sub_handle, index = 0; unsigned int irq, irq_want; struct msi_desc *msidesc; + int node, ret; + + /* Multiple MSI vectors only supported with interrupt remapping */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; node = dev_to_node(&dev->dev); irq_want = nr_irqs_gsi; - sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { irq = create_irq_nr(irq_want, node); if (irq == 0) return -ENOSPC; + irq_want = irq + 1; - if (!irq_remapping_enabled) - goto no_ir; - if (!sub_handle) { - /* - * allocate the consecutive block of IRTE's - * for 'nvec' - */ - index = msi_alloc_remapped_irq(dev, irq, nvec); - if (index < 0) { - ret = index; - goto error; - } - } else { - ret = msi_setup_remapped_irq(dev, irq, index, - sub_handle); - if (ret < 0) - goto error; - } -no_ir: ret = setup_msi_irq(dev, msidesc, irq, 0); if (ret < 0) goto error; - sub_handle++; } return 0; @@ -3244,74 +3228,6 @@ error: return ret; } -int setup_msi_irqs(struct pci_dev *dev, int nvec) -{ - int node, ret, sub_handle, index = 0; - unsigned int irq; - struct msi_desc *msidesc; - - if (nvec > 1 && !irq_remapping_enabled) - return 1; - - nvec = __roundup_pow_of_two(nvec); - - WARN_ON(!list_is_singular(&dev->msi_list)); - msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); - WARN_ON(msidesc->irq); - WARN_ON(msidesc->msi_attrib.multiple); - - node = dev_to_node(&dev->dev); - irq = __create_irqs(nr_irqs_gsi, nvec, node); - if (irq == 0) - return -ENOSPC; - - if (!irq_remapping_enabled) { - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) - goto error; - return 0; - } - - msidesc->msi_attrib.multiple = ilog2(nvec); - for (sub_handle = 0; sub_handle < nvec; sub_handle++) { - if (!sub_handle) { - index = msi_alloc_remapped_irq(dev, irq, nvec); - if (index < 0) { - ret = index; - goto error; - } - } else { - ret = msi_setup_remapped_irq(dev, irq + sub_handle, - index, sub_handle); - if (ret < 0) - goto error; - } - ret = setup_msi_irq(dev, msidesc, irq, sub_handle); - if (ret < 0) - goto error; - } - return 0; - -error: - destroy_irqs(irq, nvec); - - /* - * Restore altered MSI descriptor fields and prevent just destroyed - * IRQs from tearing down again in default_teardown_msi_irqs() - */ - msidesc->irq = 0; - msidesc->msi_attrib.multiple = 0; - - return ret; -} - -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - if (type == PCI_CAP_ID_MSI) - return setup_msi_irqs(dev, nvec); - return setup_msix_irqs(dev, nvec); -} - void native_teardown_msi_irq(unsigned int irq) { destroy_irq(irq); -- cgit v1.2.2 From 373dd7a27f2469020e7b56744cf47b82986b9749 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:39 +0200 Subject: x86, io_apic: Introduce set_affinity function pointer With interrupt remapping a special function is used to change the affinity of an IO-APIC interrupt. Abstract this with a function pointer. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 17 +++++++---------- arch/x86/kernel/x86_init.c | 1 + 2 files changed, 8 insertions(+), 10 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 d4b045e018fb..d9ca3be9636c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2369,9 +2369,10 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, return 0; } -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) + +int native_ioapic_set_affinity(struct irq_data *data, + const struct cpumask *mask, + bool force) { unsigned int dest, irq = data->irq; unsigned long flags; @@ -2570,8 +2571,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip) chip->irq_print_chip = ir_print_prefix; chip->irq_ack = ir_ack_apic_edge; chip->irq_eoi = ir_ack_apic_level; - - chip->irq_set_affinity = set_remapped_irq_affinity; + chip->irq_set_affinity = x86_io_apic_ops.set_affinity; } #endif /* CONFIG_IRQ_REMAP */ @@ -2582,7 +2582,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, - .irq_set_affinity = ioapic_set_affinity, + .irq_set_affinity = native_ioapic_set_affinity, .irq_retrigger = ioapic_retrigger_irq, }; @@ -3694,10 +3694,7 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - if (irq_remapping_enabled) - set_remapped_irq_affinity(idata, mask, false); - else - ioapic_set_affinity(idata, mask, false); + x86_io_apic_ops.set_affinity(idata, mask, false); } } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 0357eee65673..2ca3475e90a8 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -126,4 +126,5 @@ struct x86_io_apic_ops x86_io_apic_ops = { .modify = native_io_apic_modify, .disable = native_disable_io_apic, .print_entries = native_io_apic_print_entries, + .set_affinity = native_ioapic_set_affinity, }; -- cgit v1.2.2 From a6a25dd3270944f3c4182ffcbe0f60482471e849 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:40 +0200 Subject: x86, io_apic: Convert setup_ioapic_entry to function pointer This pointer is changed to a different function when IRQ remapping is enabled. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 14 +++++--------- arch/x86/kernel/x86_init.c | 1 + 2 files changed, 6 insertions(+), 9 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 d9ca3be9636c..9a7131f29c83 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1315,14 +1315,10 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, fasteoi ? "fasteoi" : "edge"); } -static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr) +int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) { - if (irq_remapping_enabled) - return setup_ioapic_remapped_entry(irq, entry, destination, - vector, attr); - memset(entry, 0, sizeof(*entry)); entry->delivery_mode = apic->irq_delivery_mode; @@ -1370,8 +1366,8 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, cfg->vector, irq, attr->trigger, attr->polarity, dest); - if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", + if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { + pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 2ca3475e90a8..06db44f4fbf5 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -127,4 +127,5 @@ struct x86_io_apic_ops x86_io_apic_ops = { .disable = native_disable_io_apic, .print_entries = native_io_apic_print_entries, .set_affinity = native_ioapic_set_affinity, + .setup_entry = native_setup_ioapic_entry, }; -- cgit v1.2.2 From 6a9f5de27216801b4e38ccd8aa0168a5dd8eca9b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:41 +0200 Subject: x86, io_apic: Move irq_remapping_enabled checks out of check_timer() Move these checks to IRQ remapping code by introducing the panic_on_irq_remap() function. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 6 ++---- 1 file changed, 2 insertions(+), 4 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 9a7131f29c83..aa2b75360115 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2777,8 +2777,7 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { - if (irq_remapping_enabled) - panic("BIOS bug: timer not connected to IO-APIC"); + panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC"); pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2810,8 +2809,7 @@ static inline void __init check_timer(void) clear_IO_APIC_pin(0, pin1); goto out; } - if (irq_remapping_enabled) - panic("timer doesn't work through Interrupt-remapped IO-APIC"); + panic_if_irq_remap("timer doesn't work through Interrupt-remapped IO-APIC"); local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) -- cgit v1.2.2 From 1d254428c0ba30a0fbb8112d875ba64f4e60db25 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:42 +0200 Subject: x86, io_apic: Remove irq_remapping_enabled check in setup_timer_IRQ0_pin This function is only called when irq-remapping is disabled. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 3 --- 1 file changed, 3 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 aa2b75360115..ee0757db34ec 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1475,9 +1475,6 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, struct IO_APIC_route_entry entry; unsigned int dest; - if (irq_remapping_enabled) - return; - memset(&entry, 0, sizeof(entry)); /* -- cgit v1.2.2 From 9b1b0e42f54bc452817f4bb6a8d939afe4f04303 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:45 +0200 Subject: x86, io-apic: Move CONFIG_IRQ_REMAP code out of x86 core Move all the code to either to the header file asm/irq_remapping.h or to drivers/iommu/. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 44 +----------------------------------------- 1 file changed, 1 insertion(+), 43 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 ee0757db34ec..0fd5f30bac7f 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -68,22 +68,6 @@ #define for_each_irq_pin(entry, head) \ for (entry = head; entry; entry = entry->next) -#ifdef CONFIG_IRQ_REMAP -static void irq_remap_modify_chip_defaults(struct irq_chip *chip); -static inline bool irq_remapped(struct irq_cfg *cfg) -{ - return cfg->irq_2_iommu.iommu != NULL; -} -#else -static inline bool irq_remapped(struct irq_cfg *cfg) -{ - return false; -} -static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) -{ -} -#endif - /* * Is the SiS APIC rmw bug present ? * -1 = don't know, 0 = no, 1 = yes @@ -606,7 +590,7 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) } } -static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { struct irq_pin_list *entry; unsigned long flags; @@ -2542,32 +2526,6 @@ static void ack_apic_level(struct irq_data *data) ioapic_irqd_unmask(data, cfg, masked); } -#ifdef CONFIG_IRQ_REMAP -static void ir_ack_apic_edge(struct irq_data *data) -{ - ack_APIC_irq(); -} - -static void ir_ack_apic_level(struct irq_data *data) -{ - ack_APIC_irq(); - eoi_ioapic_irq(data->irq, data->chip_data); -} - -static void ir_print_prefix(struct irq_data *data, struct seq_file *p) -{ - seq_printf(p, " IR-%s", data->chip->name); -} - -static void irq_remap_modify_chip_defaults(struct irq_chip *chip) -{ - chip->irq_print_chip = ir_print_prefix; - chip->irq_ack = ir_ack_apic_edge; - chip->irq_eoi = ir_ack_apic_level; - chip->irq_set_affinity = x86_io_apic_ops.set_affinity; -} -#endif /* CONFIG_IRQ_REMAP */ - static struct irq_chip ioapic_chip __read_mostly = { .name = "IO-APIC", .irq_startup = startup_ioapic_irq, -- cgit v1.2.2 From 9f9d39e403faf5e1a22334fe4df96516e4f389a8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:46 +0200 Subject: x86, io-apic: Remove !irq_remapped() check from __target_IO_APIC_irq() This function is only called from default_ioapic_set_affinity() which is only used when interrupt remapping is disabled since the introduction of the set_affinity function pointer. So the check will always evaluate as true and can be removed. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 8 ++------ 1 file changed, 2 insertions(+), 6 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 0fd5f30bac7f..5b7eb70c143c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2299,12 +2299,8 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq apic = entry->apic; pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); + + io_apic_write(apic, 0x11 + pin*2, dest); reg = io_apic_read(apic, 0x10 + pin*2); reg &= ~IO_APIC_REDIR_VECTOR_MASK; reg |= vector; -- cgit v1.2.2 From 11b4a1cc3836ac71a214446d350e923c76012368 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:47 +0200 Subject: x86, irq: Move irq_remapped() check into free_remapped_irq The function is called unconditionally now in IO-APIC code removing another irq_remapped() check from x86 core code. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 4 ++-- 1 file changed, 2 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 5b7eb70c143c..110483906dd3 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3003,8 +3003,8 @@ void destroy_irq(unsigned int irq) irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - if (irq_remapped(cfg)) - free_remapped_irq(irq); + free_remapped_irq(irq); + raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); raw_spin_unlock_irqrestore(&vector_lock, flags); -- cgit v1.2.2 From 2976fd8417f5744de3bb9109e4f30f353a36b1c0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:48 +0200 Subject: x86, irq: Introduce setup_remapped_irq() This function does irq-remapping specific interrupt setup like modifying the chip defaults. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 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 110483906dd3..372512219a9b 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1288,11 +1288,8 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, fasteoi = false; } - if (irq_remapped(cfg)) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); + if (setup_remapped_irq(irq, cfg, chip)) fasteoi = trigger != 0; - } hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; irq_set_chip_and_handler_name(irq, chip, hdl, @@ -3131,10 +3128,7 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, if (!irq_offset) write_msi_msg(irq, &msg); - if (irq_remapped(irq_get_chip_data(irq))) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); - } + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); @@ -3272,8 +3266,7 @@ int default_setup_hpet_msi(unsigned int irq, unsigned int id) hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - if (irq_remapped(irq_get_chip_data(irq))) - irq_remap_modify_chip_defaults(chip); + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; -- cgit v1.2.2 From 7601384f91be1a5ea60cb4ef6e28cad628e6cd1e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:49 +0200 Subject: x86, msi: Introduce x86_msi.compose_msi_msg call-back This call-back points to the right function for initializing the msi_msg structure. The old code for msi_msg generation was split up into the irq-remapped and the default case. The irq-remapped case just calls into the specific Intel or AMD implementation when the device is behind an IOMMU. Otherwise the default function is called. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 57 ++++++++++++++++++++++-------------------- arch/x86/kernel/x86_init.c | 1 + 2 files changed, 31 insertions(+), 27 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 372512219a9b..b832810d28f0 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3019,37 +3019,16 @@ void destroy_irqs(unsigned int irq, unsigned int count) /* * MSI message composition */ -#ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) +void native_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id) { - struct irq_cfg *cfg; - int err; - unsigned dest; + struct irq_cfg *cfg = irq_cfg(irq); - if (disable_apic) - return -ENXIO; - - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; - - if (irq_remapped(cfg)) { - compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); - return 0; - } + msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) - msg->address_hi = MSI_ADDR_BASE_HI | - MSI_ADDR_EXT_DEST_ID(dest); - else - msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); msg->address_lo = MSI_ADDR_BASE_LO | @@ -3068,6 +3047,30 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, MSI_DATA_DELIVERY_FIXED: MSI_DATA_DELIVERY_LOWPRI) | MSI_DATA_VECTOR(cfg->vector); +} + +#ifdef CONFIG_PCI_MSI +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg; + int err; + unsigned dest; + + if (disable_apic) + return -ENXIO; + + cfg = irq_cfg(irq); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; + + x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); return 0; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 06db44f4fbf5..ee4a17c22569 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -113,6 +113,7 @@ struct x86_platform_ops x86_platform = { EXPORT_SYMBOL_GPL(x86_platform); struct x86_msi_ops x86_msi = { .setup_msi_irqs = native_setup_msi_irqs, + .compose_msi_msg = native_compose_msi_msg, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, -- cgit v1.2.2 From da165322dfb6cbc50042b1051f07b837a26f3bb8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 26 Sep 2012 12:44:50 +0200 Subject: x86, io_apic: Introduce eoi_ioapic_pin call-back This callback replaces the old __eoi_ioapic_pin function which needs a special path for interrupt remapping. Signed-off-by: Joerg Roedel Acked-by: Sebastian Andrzej Siewior Reviewed-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/apic/io_apic.c | 20 ++++++-------------- arch/x86/kernel/x86_init.c | 1 + 2 files changed, 7 insertions(+), 14 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 b832810d28f0..9ed796ccc32c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -310,7 +310,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -static inline void io_apic_eoi(unsigned int apic, unsigned int vector) +void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); @@ -557,19 +557,10 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) +void native_eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { - /* - * Intr-remapping uses pin number as the virtual vector - * in the RTE. Actual vector is programmed in - * intr-remapping table entry. Hence for the io-apic - * EOI we use the pin number. - */ - if (cfg && irq_remapped(cfg)) - io_apic_eoi(apic, pin); - else - io_apic_eoi(apic, vector); + io_apic_eoi(apic, vector); } else { struct IO_APIC_route_entry entry, entry1; @@ -597,7 +588,8 @@ void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) raw_spin_lock_irqsave(&ioapic_lock, flags); for_each_irq_pin(entry, cfg->irq_2_pin) - __eoi_ioapic_pin(entry->apic, entry->pin, cfg->vector, cfg); + x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, + cfg->vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -634,7 +626,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) } raw_spin_lock_irqsave(&ioapic_lock, flags); - __eoi_ioapic_pin(apic, pin, entry.vector, NULL); + x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ee4a17c22569..d065d67c2672 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -129,4 +129,5 @@ struct x86_io_apic_ops x86_io_apic_ops = { .print_entries = native_io_apic_print_entries, .set_affinity = native_ioapic_set_affinity, .setup_entry = native_setup_ioapic_entry, + .eoi_ioapic_pin = native_eoi_ioapic_pin, }; -- cgit v1.2.2 From 5dcd14ecd41ea2b3ae3295a9b30d98769d52165f Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 29 Jan 2013 01:05:24 -0800 Subject: x86, boot: Sanitize boot_params if not zeroed on creation Use the new sentinel field to detect bootloaders which fail to follow protocol and don't initialize fields in struct boot_params that they do not explicitly initialize to zero. Based on an original patch and research by Yinghai Lu. Changed by hpa to be invoked both in the decompression path and in the kernel proper; the latter for the case where a bootloader takes over decompression. Originally-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-26-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head32.c | 3 +++ arch/x86/kernel/head64.c | 2 ++ 2 files changed, 5 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index c18f59d10101..6773c918b8cc 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -18,6 +18,7 @@ #include #include #include +#include static void __init i386_default_early_setup(void) { @@ -30,6 +31,8 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { + sanitize_boot_params(&boot_params); + memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 037df57a99ac..849fc9e63c2f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -25,6 +25,7 @@ #include #include #include +#include static void __init zap_identity_mappings(void) { @@ -46,6 +47,7 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; memcpy(&boot_params, real_mode_data, sizeof boot_params); + sanitize_boot_params(&boot_params); if (boot_params.hdr.cmd_line_ptr) { command_line = __va(boot_params.hdr.cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); -- cgit v1.2.2 From b422a3091748c38b68052e8ba021652590b1f25c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:45 -0800 Subject: x86: Factor out e820_add_kernel_range() Separate out the reservation of the kernel static memory areas into a separate function. Also add support for case when memmap=xxM$yyM is used without exactmap. Need to remove reserved range at first before we add E820_RAM range, otherwise added E820_RAM range will be ignored. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-5-git-send-email-yinghai@kernel.org Cc: Jacob Shin Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 268193746cd8..5552d04b0cc1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -702,6 +702,27 @@ static void __init trim_bios_range(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } +/* called before trim_bios_range() to spare extra sanitize */ +static void __init e820_add_kernel_range(void) +{ + u64 start = __pa_symbol(_text); + u64 size = __pa_symbol(_end) - start; + + /* + * Complain if .text .data and .bss are not marked as E820_RAM and + * attempt to fix it by adding the range. We may have a confused BIOS, + * or the user may have used memmap=exactmap or memmap=xxM$yyM to + * exclude kernel range. If we really are running on top non-RAM, + * we will crash later anyways. + */ + if (e820_all_mapped(start, start + size, E820_RAM)) + return; + + pr_warn(".text .data .bss are not marked as E820_RAM!\n"); + e820_remove_range(start, size, E820_RAM, 0); + e820_add_region(start, size, E820_RAM); +} + static int __init parse_reservelow(char *p) { unsigned long long size; @@ -897,20 +918,7 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - /* - * Complain if .text .data and .bss are not marked as E820_RAM and - * attempt to fix it by adding the range. We may have a confused BIOS, - * or the user may have incorrectly supplied it via memmap=exactmap. If - * we really are running on top non-RAM, we will crash later anyways. - */ - if (!e820_all_mapped(code_resource.start, __pa(__brk_limit), E820_RAM)) { - pr_warn(".text .data .bss are not marked as E820_RAM!\n"); - - e820_add_region(code_resource.start, - __pa(__brk_limit) - code_resource.start + 1, - E820_RAM); - } - + e820_add_kernel_range(); trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { -- cgit v1.2.2 From fa2bbce985ca97943305cdc81d9626e6810ed7f2 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:49 -0800 Subject: x86, 64bit: Copy struct boot_params early We want to support struct boot_params (formerly known as the zero-page, or real-mode data) above the 4 GiB mark. We will have #PF handler to set page table for not accessible ram early, but want to limit it before x86_64_start_reservations to limit the code change to native path only. Also we will need the ramdisk info in struct boot_params to access the microcode blob in ramdisk in x86_64_start_kernel, so copy struct boot_params early makes it accessing ramdisk info simple. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-9-git-send-email-yinghai@kernel.org Cc: Alexander Duyck Cc: Fenghua Yu Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 849fc9e63c2f..7785e66840a4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -89,6 +89,8 @@ void __init x86_64_start_kernel(char * real_mode_data) } load_idt((const struct desc_ptr *)&idt_descr); + copy_bootdata(__va(real_mode_data)); + if (console_loglevel == 10) early_printk("Kernel alive\n"); @@ -97,7 +99,9 @@ void __init x86_64_start_kernel(char * real_mode_data) void __init x86_64_start_reservations(char *real_mode_data) { - copy_bootdata(__va(real_mode_data)); + /* version is always not zero if it is copied */ + if (!boot_params.hdr.version) + copy_bootdata(__va(real_mode_data)); memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); -- cgit v1.2.2 From 4f7b92263ad68cdc72b11808320d9c881bfa857e Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:51 -0800 Subject: x86, realmode: Separate real_mode reserve and setup After we switch to use #PF handler help to set page table, init_level4_pgt will only have entries set after init_mem_mapping(). We need to move copying init_level4_pgt to trampoline_pgd after that. So split reserve and setup, and move the setup after init_mem_mapping() Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-11-git-send-email-yinghai@kernel.org Cc: Jarkko Sakkinen Acked-by: Jarkko Sakkinen Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5552d04b0cc1..85a8290801df 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -999,12 +999,14 @@ void __init setup_arch(char **cmdline_p) printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped< Date: Thu, 24 Jan 2013 12:19:52 -0800 Subject: x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 81 ++++++++++++++++-- arch/x86/kernel/head_64.S | 210 ++++++++++++++++++++++++++++------------------ arch/x86/kernel/setup.c | 2 + arch/x86/kernel/traps.c | 9 ++ 4 files changed, 212 insertions(+), 90 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7785e66840a4..f57df05ea126 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -27,11 +27,73 @@ #include #include -static void __init zap_identity_mappings(void) +/* + * Manage page tables very early on. + */ +extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; +static unsigned int __initdata next_early_pgt = 2; + +/* Wipe all early page tables except for the kernel symbol map */ +static void __init reset_early_page_tables(void) { - pgd_t *pgd = pgd_offset_k(0UL); - pgd_clear(pgd); - __flush_tlb_all(); + unsigned long i; + + for (i = 0; i < PTRS_PER_PGD-1; i++) + early_level4_pgt[i].pgd = 0; + + next_early_pgt = 0; + + write_cr3(__pa(early_level4_pgt)); +} + +/* Create a new PMD entry */ +int __init early_make_pgtable(unsigned long address) +{ + unsigned long physaddr = address - __PAGE_OFFSET; + unsigned long i; + pgdval_t pgd, *pgd_p; + pudval_t *pud_p; + pmdval_t pmd, *pmd_p; + + /* Invalid address or early pgt is done ? */ + if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt)) + return -1; + + i = (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); + pgd_p = &early_level4_pgt[i].pgd; + pgd = *pgd_p; + + /* + * The use of __START_KERNEL_map rather than __PAGE_OFFSET here is + * critical -- __PAGE_OFFSET would point us back into the dynamic + * range and we might end up looping forever... + */ + if (pgd && next_early_pgt < EARLY_DYNAMIC_PAGE_TABLES) { + pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + } else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES-1) + reset_early_page_tables(); + + pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; + for (i = 0; i < PTRS_PER_PUD; i++) + pud_p[i] = 0; + + *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + i = (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); + pud_p += i; + + pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++]; + pmd = (physaddr & PUD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL); + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd_p[i] = pmd; + pmd += PMD_SIZE; + } + + *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + + return 0; } /* Don't add a printk in there. printk relies on the PDA which is not initialized @@ -72,12 +134,13 @@ void __init x86_64_start_kernel(char * real_mode_data) (__START_KERNEL & PGDIR_MASK))); BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); + /* Kill off the identity-map trampoline */ + reset_early_page_tables(); + /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); - /* Make NULL pointers segfault */ - zap_identity_mappings(); - + /* XXX - this is wrong... we need to build page tables from scratch */ max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { @@ -94,6 +157,10 @@ void __init x86_64_start_kernel(char * real_mode_data) if (console_loglevel == 10) early_printk("Kernel alive\n"); + clear_page(init_level4_pgt); + /* set init_level4_pgt kernel high mapping*/ + init_level4_pgt[511] = early_level4_pgt[511]; + x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 980053c4b9cc..d94f6d68be2a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -47,14 +47,13 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .code64 .globl startup_64 startup_64: - /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1, * and someone has loaded an identity mapped page table * for us. These identity mapped page tables map all of the * kernel pages and possibly all of memory. * - * %esi holds a physical pointer to real_mode_data. + * %rsi holds a physical pointer to real_mode_data. * * We come here either directly from a 64bit bootloader, or from * arch/x86_64/boot/compressed/head.S. @@ -66,7 +65,8 @@ startup_64: * tables and then reload them. */ - /* Compute the delta between the address I am compiled to run at and the + /* + * Compute the delta between the address I am compiled to run at and the * address I am actually running at. */ leaq _text(%rip), %rbp @@ -78,45 +78,62 @@ startup_64: testl %eax, %eax jnz bad_address - /* Is the address too large? */ - leaq _text(%rip), %rdx - movq $PGDIR_SIZE, %rax - cmpq %rax, %rdx - jae bad_address - - /* Fixup the physical addresses in the page table + /* + * Is the address too large? */ - addq %rbp, init_level4_pgt + 0(%rip) - addq %rbp, init_level4_pgt + (L4_PAGE_OFFSET*8)(%rip) - addq %rbp, init_level4_pgt + (L4_START_KERNEL*8)(%rip) + leaq _text(%rip), %rax + shrq $MAX_PHYSMEM_BITS, %rax + jnz bad_address - addq %rbp, level3_ident_pgt + 0(%rip) + /* + * Fixup the physical addresses in the page table + */ + addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip) addq %rbp, level3_kernel_pgt + (510*8)(%rip) addq %rbp, level3_kernel_pgt + (511*8)(%rip) addq %rbp, level2_fixmap_pgt + (506*8)(%rip) - /* Add an Identity mapping if I am above 1G */ + /* + * Set up the identity mapping for the switchover. These + * entries should *NOT* have the global bit set! This also + * creates a bunch of nonsense entries but that is fine -- + * it avoids problems around wraparound. + */ leaq _text(%rip), %rdi - andq $PMD_PAGE_MASK, %rdi + leaq early_level4_pgt(%rip), %rbx movq %rdi, %rax - shrq $PUD_SHIFT, %rax - andq $(PTRS_PER_PUD - 1), %rax - jz ident_complete + shrq $PGDIR_SHIFT, %rax - leaq (level2_spare_pgt - __START_KERNEL_map + _KERNPG_TABLE)(%rbp), %rdx - leaq level3_ident_pgt(%rip), %rbx - movq %rdx, 0(%rbx, %rax, 8) + leaq (4096 + _KERNPG_TABLE)(%rbx), %rdx + movq %rdx, 0(%rbx,%rax,8) + movq %rdx, 8(%rbx,%rax,8) + addq $4096, %rdx movq %rdi, %rax - shrq $PMD_SHIFT, %rax - andq $(PTRS_PER_PMD - 1), %rax - leaq __PAGE_KERNEL_IDENT_LARGE_EXEC(%rdi), %rdx - leaq level2_spare_pgt(%rip), %rbx - movq %rdx, 0(%rbx, %rax, 8) -ident_complete: + shrq $PUD_SHIFT, %rax + andl $(PTRS_PER_PUD-1), %eax + movq %rdx, (4096+0)(%rbx,%rax,8) + movq %rdx, (4096+8)(%rbx,%rax,8) + + addq $8192, %rbx + movq %rdi, %rax + shrq $PMD_SHIFT, %rdi + addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax + leaq (_end - 1)(%rip), %rcx + shrq $PMD_SHIFT, %rcx + subq %rdi, %rcx + incl %ecx + +1: + andq $(PTRS_PER_PMD - 1), %rdi + movq %rax, (%rbx,%rdi,8) + incq %rdi + addq $PMD_SIZE, %rax + decl %ecx + jnz 1b /* * Fixup the kernel text+data virtual addresses. Note that @@ -124,7 +141,6 @@ ident_complete: * cleanup_highmap() fixes this up along with the mappings * beyond _end. */ - leaq level2_kernel_pgt(%rip), %rdi leaq 4096(%rdi), %r8 /* See if it is a valid page table entry */ @@ -139,17 +155,14 @@ ident_complete: /* Fixup phys_base */ addq %rbp, phys_base(%rip) - /* Due to ENTRY(), sometimes the empty space gets filled with - * zeros. Better take a jmp than relying on empty space being - * filled with 0x90 (nop) - */ - jmp secondary_startup_64 + movq $(early_level4_pgt - __START_KERNEL_map), %rax + jmp 1f ENTRY(secondary_startup_64) /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1, * and someone has loaded a mapped page table. * - * %esi holds a physical pointer to real_mode_data. + * %rsi holds a physical pointer to real_mode_data. * * We come here either from startup_64 (using physical addresses) * or from trampoline.S (using virtual addresses). @@ -159,12 +172,14 @@ ENTRY(secondary_startup_64) * after the boot processor executes this code. */ + movq $(init_level4_pgt - __START_KERNEL_map), %rax +1: + /* Enable PAE mode and PGE */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %eax - movq %rax, %cr4 + movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + movq %rcx, %cr4 /* Setup early boot stage 4 level pagetables. */ - movq $(init_level4_pgt - __START_KERNEL_map), %rax addq phys_base(%rip), %rax movq %rax, %cr3 @@ -196,7 +211,7 @@ ENTRY(secondary_startup_64) movq %rax, %cr0 /* Setup a boot time stack */ - movq stack_start(%rip),%rsp + movq stack_start(%rip), %rsp /* zero EFLAGS after setting rsp */ pushq $0 @@ -236,15 +251,33 @@ ENTRY(secondary_startup_64) movl initial_gs+4(%rip),%edx wrmsr - /* esi is pointer to real mode structure with interesting info. + /* rsi is pointer to real mode structure with interesting info. pass it to C */ - movl %esi, %edi + movq %rsi, %rdi /* Finally jump to run C code and to be on real kernel address * Since we are running on identity-mapped space we have to jump * to the full 64bit address, this is only possible as indirect * jump. In addition we need to ensure %cs is set so we make this * a far return. + * + * Note: do not change to far jump indirect with 64bit offset. + * + * AMD does not support far jump indirect with 64bit offset. + * AMD64 Architecture Programmer's Manual, Volume 3: states only + * JMP FAR mem16:16 FF /5 Far jump indirect, + * with the target specified by a far pointer in memory. + * JMP FAR mem16:32 FF /5 Far jump indirect, + * with the target specified by a far pointer in memory. + * + * Intel64 does support 64bit offset. + * Software Developer Manual Vol 2: states: + * FF /5 JMP m16:16 Jump far, absolute indirect, + * address given in m16:16 + * FF /5 JMP m16:32 Jump far, absolute indirect, + * address given in m16:32. + * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect, + * address given in m16:64. */ movq initial_code(%rip),%rax pushq $0 # fake return address to stop unwinder @@ -270,13 +303,13 @@ ENDPROC(start_cpu0) /* SMP bootup changes these two */ __REFDATA - .align 8 - ENTRY(initial_code) + .balign 8 + GLOBAL(initial_code) .quad x86_64_start_kernel - ENTRY(initial_gs) + GLOBAL(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - ENTRY(stack_start) + GLOBAL(stack_start) .quad init_thread_union+THREAD_SIZE-8 .word 0 __FINITDATA @@ -284,7 +317,7 @@ ENDPROC(start_cpu0) bad_address: jmp bad_address - .section ".init.text","ax" + __INIT .globl early_idt_handlers early_idt_handlers: # 104(%rsp) %rflags @@ -321,14 +354,22 @@ ENTRY(early_idt_handler) pushq %r11 # 0(%rsp) cmpl $__KERNEL_CS,96(%rsp) - jne 10f + jne 11f + + cmpl $14,72(%rsp) # Page fault? + jnz 10f + GET_CR2_INTO(%rdi) # can clobber any volatile register if pv + call early_make_pgtable + andl %eax,%eax + jz 20f # All good +10: leaq 88(%rsp),%rdi # Pointer to %rip call early_fixup_exception andl %eax,%eax jnz 20f # Found an exception entry -10: +11: #ifdef CONFIG_EARLY_PRINTK GET_CR2_INTO(%r9) # can clobber any volatile register if pv movl 80(%rsp),%r8d # error code @@ -350,7 +391,7 @@ ENTRY(early_idt_handler) 1: hlt jmp 1b -20: # Exception table entry found +20: # Exception table entry found or page table generated popq %r11 popq %r10 popq %r9 @@ -364,6 +405,8 @@ ENTRY(early_idt_handler) decl early_recursion_flag(%rip) INTERRUPT_RETURN + __INITDATA + .balign 4 early_recursion_flag: .long 0 @@ -374,11 +417,10 @@ early_idt_msg: early_idt_ripmsg: .asciz "RIP %s\n" #endif /* CONFIG_EARLY_PRINTK */ - .previous #define NEXT_PAGE(name) \ .balign PAGE_SIZE; \ -ENTRY(name) +GLOBAL(name) /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ @@ -388,24 +430,37 @@ ENTRY(name) i = i + 1 ; \ .endr + __INITDATA +NEXT_PAGE(early_level4_pgt) + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + +NEXT_PAGE(early_dynamic_pgts) + .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 + .data - /* - * This default setting generates an ident mapping at address 0x100000 - * and a mapping for the kernel that precisely maps virtual address - * 0xffffffff80000000 to physical address 0x000000. (always using - * 2Mbyte large pages provided by PAE mode) - */ + +#ifndef CONFIG_XEN NEXT_PAGE(init_level4_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_START_KERNEL*8, 0 + .fill 512,8,0 +#else +NEXT_PAGE(init_level4_pgt) + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .org init_level4_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .fill 511,8,0 + .fill 511, 8, 0 +NEXT_PAGE(level2_ident_pgt) + /* Since I easily can, map the first 1G. + * Don't set NX because code runs from these pages. + */ + PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +#endif NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 @@ -413,21 +468,6 @@ NEXT_PAGE(level3_kernel_pgt) .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE -NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 - -NEXT_PAGE(level1_fixmap_pgt) - .fill 512,8,0 - -NEXT_PAGE(level2_ident_pgt) - /* Since I easily can, map the first 1G. - * Don't set NX because code runs from these pages. - */ - PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) - NEXT_PAGE(level2_kernel_pgt) /* * 512 MB kernel mapping. We spend a full page on this pagetable @@ -442,11 +482,16 @@ NEXT_PAGE(level2_kernel_pgt) PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) -NEXT_PAGE(level2_spare_pgt) - .fill 512, 8, 0 +NEXT_PAGE(level2_fixmap_pgt) + .fill 506,8,0 + .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ + .fill 5,8,0 + +NEXT_PAGE(level1_fixmap_pgt) + .fill 512,8,0 #undef PMDS -#undef NEXT_PAGE .data .align 16 @@ -472,6 +517,5 @@ ENTRY(nmi_idt_table) .skip IDT_ENTRIES * 16 __PAGE_ALIGNED_BSS - .align PAGE_SIZE -ENTRY(empty_zero_page) +NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 85a8290801df..db9c41dae8d7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1005,6 +1005,8 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); + early_trap_pf_init(); + setup_real_mode(); memblock.current_limit = get_max_mapped(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ecffca11f4e9..68bda7a84159 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -688,10 +688,19 @@ void __init early_trap_init(void) set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); /* int3 can be called from all */ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); +#ifdef CONFIG_X86_32 set_intr_gate(X86_TRAP_PF, &page_fault); +#endif load_idt(&idt_descr); } +void __init early_trap_pf_init(void) +{ +#ifdef CONFIG_X86_64 + set_intr_gate(X86_TRAP_PF, &page_fault); +#endif +} + void __init trap_init(void) { int i; -- cgit v1.2.2 From 6b9c75aca6cba4d99a6e8d8274b1788d4d4b50d9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:53 -0800 Subject: x86, 64bit: #PF handler set page to cover only 2M per #PF We only map a single 2 MiB page per #PF, even though we should be able to do this a full gigabyte at a time with no additional memory cost. This is a workaround for a broken AMD reference BIOS (and its derivatives in shipping system) which maps a large chunk of memory as WB in the MTRR system but will #MC if the processor wanders off and tries to prefetch that memory, which can happen any time the memory is mapped in the TLB. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-13-git-send-email-yinghai@kernel.org Cc: Alexander Duyck [ hpa: rewrote the patch description ] Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 42 +++++++++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 17 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f57df05ea126..816fc85c9bb3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -53,15 +53,15 @@ int __init early_make_pgtable(unsigned long address) unsigned long physaddr = address - __PAGE_OFFSET; unsigned long i; pgdval_t pgd, *pgd_p; - pudval_t *pud_p; + pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt)) return -1; - i = (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); - pgd_p = &early_level4_pgt[i].pgd; +again: + pgd_p = &early_level4_pgt[pgd_index(address)].pgd; pgd = *pgd_p; /* @@ -69,29 +69,37 @@ int __init early_make_pgtable(unsigned long address) * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (pgd && next_early_pgt < EARLY_DYNAMIC_PAGE_TABLES) { + if (pgd) pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); - } else { - if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES-1) + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { reset_early_page_tables(); + goto again; + } pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; for (i = 0; i < PTRS_PER_PUD; i++) pud_p[i] = 0; - *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - i = (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); - pud_p += i; - - pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++]; - pmd = (physaddr & PUD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL); - for (i = 0; i < PTRS_PER_PMD; i++) { - pmd_p[i] = pmd; - pmd += PMD_SIZE; - } + pud_p += pud_index(address); + pud = *pud_p; - *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + if (pud) + pmd_p = (pmdval_t *)((pud & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { + reset_early_page_tables(); + goto again; + } + + pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++]; + for (i = 0; i < PTRS_PER_PMD; i++) + pmd_p[i] = 0; + *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL); + pmd_p[pmd_index(address)] = pmd; return 0; } -- cgit v1.2.2 From 100542306f644fc580857a8ca4896fb12b794d41 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:54 -0800 Subject: x86, 64bit: Don't set max_pfn_mapped wrong value early on native path We are not having max_pfn_mapped set correctly until init_memory_mapping. So don't print its initial value for 64bit Also need to use KERNEL_IMAGE_SIZE directly for highmap cleanup. -v2: update comments about max_pfn_mapped according to Stefano Stabellini. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-14-git-send-email-yinghai@kernel.org Acked-by: Borislav Petkov Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 3 --- arch/x86/kernel/setup.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 816fc85c9bb3..f3b19685918e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -148,9 +148,6 @@ void __init x86_64_start_kernel(char * real_mode_data) /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); - /* XXX - this is wrong... we need to build page tables from scratch */ - max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { #ifdef CONFIG_EARLY_PRINTK set_intr_gate(i, &early_idt_handlers[i]); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index db9c41dae8d7..d58083a2e158 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -996,8 +996,10 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif +#ifdef CONFIG_X86_32 printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped< Date: Thu, 24 Jan 2013 12:19:55 -0800 Subject: x86: Merge early_reserve_initrd for 32bit and 64bit They are the same, could move them out from head32/64.c to setup.c. We are using memblock, and it could handle overlapping properly, so we don't need to reserve some at first to hold the location, and just need to make sure we reserve them before we are using memblock to find free mem to use. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-15-git-send-email-yinghai@kernel.org Reviewed-by: Pekka Enberg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head32.c | 11 ----------- arch/x86/kernel/head64.c | 11 ----------- arch/x86/kernel/setup.c | 22 ++++++++++++++++++---- 3 files changed, 18 insertions(+), 26 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 6773c918b8cc..a795b54de7d3 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -36,17 +36,6 @@ void __init i386_start_kernel(void) memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); -#ifdef CONFIG_BLK_DEV_INITRD - /* Reserve INITRD */ - if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { - /* Assume only end is not page aligned */ - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; - u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); - } -#endif - /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_MRST: diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f3b19685918e..b88a1fab2158 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -178,17 +178,6 @@ void __init x86_64_start_reservations(char *real_mode_data) memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); -#ifdef CONFIG_BLK_DEV_INITRD - /* Reserve INITRD */ - if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { - /* Assume only end is not page aligned */ - unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; - unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; - unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); - } -#endif - reserve_ebda_region(); /* diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d58083a2e158..8e356923cbd0 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -360,6 +360,19 @@ static u64 __init get_mem_size(unsigned long limit_pfn) return mapped_pages << PAGE_SHIFT; } +static void __init early_reserve_initrd(void) +{ + /* Assume only end is not page aligned */ + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); + + if (!boot_params.hdr.type_of_loader || + !ramdisk_image || !ramdisk_size) + return; /* No initrd provided by bootloader */ + + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); +} static void __init reserve_initrd(void) { /* Assume only end is not page aligned */ @@ -386,10 +399,6 @@ static void __init reserve_initrd(void) if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image), PFN_DOWN(ramdisk_end))) { /* All are mapped, easy case */ - /* - * don't need to reserve again, already reserved early - * in i386_start_kernel - */ initrd_start = ramdisk_image + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; return; @@ -400,6 +409,9 @@ static void __init reserve_initrd(void) memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else +static void __init early_reserve_initrd(void) +{ +} static void __init reserve_initrd(void) { } @@ -760,6 +772,8 @@ early_param("reservelow", parse_reservelow); void __init setup_arch(char **cmdline_p) { + early_reserve_initrd(); + #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); -- cgit v1.2.2 From a8a51a88d5152aa40e5e07dcdd939c7fafc42224 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:56 -0800 Subject: x86: Add get_ramdisk_image/size() There are several places to find ramdisk information early for reserving and relocating. Use accessor functions to make code more readable and consistent. Later will add ext_ramdisk_image/size in those functions to support loading ramdisk above 4g. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-16-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 8e356923cbd0..83b38617ff59 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -294,12 +294,25 @@ static void __init reserve_brk(void) #ifdef CONFIG_BLK_DEV_INITRD +static u64 __init get_ramdisk_image(void) +{ + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + + return ramdisk_image; +} +static u64 __init get_ramdisk_size(void) +{ + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + + return ramdisk_size; +} + #define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) static void __init relocate_initrd(void) { /* Assume only end is not page aligned */ - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); u64 ramdisk_here; unsigned long slop, clen, mapaddr; @@ -338,8 +351,8 @@ static void __init relocate_initrd(void) ramdisk_size -= clen; } - ramdisk_image = boot_params.hdr.ramdisk_image; - ramdisk_size = boot_params.hdr.ramdisk_size; + ramdisk_image = get_ramdisk_image(); + ramdisk_size = get_ramdisk_size(); printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, @@ -363,8 +376,8 @@ static u64 __init get_mem_size(unsigned long limit_pfn) static void __init early_reserve_initrd(void) { /* Assume only end is not page aligned */ - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); if (!boot_params.hdr.type_of_loader || @@ -376,8 +389,8 @@ static void __init early_reserve_initrd(void) static void __init reserve_initrd(void) { /* Assume only end is not page aligned */ - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); u64 mapped_size; -- cgit v1.2.2 From f1da834cd902f5e5df0b11a3948fc43c6071b590 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:19:57 -0800 Subject: x86, boot: Add get_cmd_line_ptr() Add an accessor function for the command line address. Later we will add support for holding a 64-bit address via ext_cmd_line_ptr. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-17-git-send-email-yinghai@kernel.org Cc: Gokul Caushik Cc: Josh Triplett Cc: Joe Millenbach Cc: Alexander Duyck Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index b88a1fab2158..62c8ce44cac4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -112,14 +112,23 @@ static void __init clear_bss(void) (unsigned long) __bss_stop - (unsigned long) __bss_start); } +static unsigned long get_cmd_line_ptr(void) +{ + unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr; + + return cmd_line_ptr; +} + static void __init copy_bootdata(char *real_mode_data) { char * command_line; + unsigned long cmd_line_ptr; memcpy(&boot_params, real_mode_data, sizeof boot_params); sanitize_boot_params(&boot_params); - if (boot_params.hdr.cmd_line_ptr) { - command_line = __va(boot_params.hdr.cmd_line_ptr); + cmd_line_ptr = get_cmd_line_ptr(); + if (cmd_line_ptr) { + command_line = __va(cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } } -- cgit v1.2.2 From 084d1283986a530828b8898f206adf44d5d3146d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:03 -0800 Subject: x86, kexec: Set ident mapping for kernel that is above max_pfn When first kernel is booted with memmap= or mem= to limit max_pfn. kexec can load second kernel above that max_pfn. We need to set ident mapping for whole image in this case instead of just for first 2M. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-23-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/machine_kexec_64.c | 43 ++++++++++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index b3ea9db39db6..be14ee120c43 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -56,6 +56,25 @@ out: return result; } +static int ident_mapping_init(struct kimage *image, pgd_t *level4p, + unsigned long mstart, unsigned long mend) +{ + int result; + + mstart = round_down(mstart, PMD_SIZE); + mend = round_up(mend - 1, PMD_SIZE); + + while (mstart < mend) { + result = init_one_level2_page(image, level4p, mstart); + if (result) + return result; + + mstart += PMD_SIZE; + } + + return 0; +} + static void init_level2_page(pmd_t *level2p, unsigned long addr) { unsigned long end_addr; @@ -184,22 +203,34 @@ err: return result; } - static int init_pgtable(struct kimage *image, unsigned long start_pgtable) { + unsigned long mstart, mend; pgd_t *level4p; int result; + int i; + level4p = (pgd_t *)__va(start_pgtable); result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); if (result) return result; + /* - * image->start may be outside 0 ~ max_pfn, for example when - * jump back to original kernel from kexeced kernel + * segments's mem ranges could be outside 0 ~ max_pfn, + * for example when jump back to original kernel from kexeced kernel. + * or first kernel is booted with user mem map, and second kernel + * could be loaded out of that range. */ - result = init_one_level2_page(image, level4p, image->start); - if (result) - return result; + for (i = 0; i < image->nr_segments; i++) { + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + + result = ident_mapping_init(image, level4p, mstart, mend); + + if (result) + return result; + } + return init_transition_pgtable(image, level4p); } -- cgit v1.2.2 From 9ebdc79f7a177d3098b89ba8ef2dd2b235163685 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:04 -0800 Subject: x86, kexec: Replace ident_mapping_init and init_level4_page Now ident_mapping_init is checking if pgd/pud is present for every 2M, so several 2Ms are in same PUD, it will keep checking if pud is there with same pud. init_level4_page just does not check existing pgd/pud. We could use generic mapping_init with different settings in info to replace those two local grown version functions. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-24-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/machine_kexec_64.c | 161 ++++++------------------------------- 1 file changed, 26 insertions(+), 135 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index be14ee120c43..d2d7e023a8c8 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -16,144 +16,12 @@ #include #include +#include #include #include #include #include -static int init_one_level2_page(struct kimage *image, pgd_t *pgd, - unsigned long addr) -{ - pud_t *pud; - pmd_t *pmd; - struct page *page; - int result = -ENOMEM; - - addr &= PMD_MASK; - pgd += pgd_index(addr); - if (!pgd_present(*pgd)) { - page = kimage_alloc_control_pages(image, 0); - if (!page) - goto out; - pud = (pud_t *)page_address(page); - clear_page(pud); - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); - } - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) { - page = kimage_alloc_control_pages(image, 0); - if (!page) - goto out; - pmd = (pmd_t *)page_address(page); - clear_page(pmd); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); - } - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); - result = 0; -out: - return result; -} - -static int ident_mapping_init(struct kimage *image, pgd_t *level4p, - unsigned long mstart, unsigned long mend) -{ - int result; - - mstart = round_down(mstart, PMD_SIZE); - mend = round_up(mend - 1, PMD_SIZE); - - while (mstart < mend) { - result = init_one_level2_page(image, level4p, mstart); - if (result) - return result; - - mstart += PMD_SIZE; - } - - return 0; -} - -static void init_level2_page(pmd_t *level2p, unsigned long addr) -{ - unsigned long end_addr; - - addr &= PAGE_MASK; - end_addr = addr + PUD_SIZE; - while (addr < end_addr) { - set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); - addr += PMD_SIZE; - } -} - -static int init_level3_page(struct kimage *image, pud_t *level3p, - unsigned long addr, unsigned long last_addr) -{ - unsigned long end_addr; - int result; - - result = 0; - addr &= PAGE_MASK; - end_addr = addr + PGDIR_SIZE; - while ((addr < last_addr) && (addr < end_addr)) { - struct page *page; - pmd_t *level2p; - - page = kimage_alloc_control_pages(image, 0); - if (!page) { - result = -ENOMEM; - goto out; - } - level2p = (pmd_t *)page_address(page); - init_level2_page(level2p, addr); - set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE)); - addr += PUD_SIZE; - } - /* clear the unused entries */ - while (addr < end_addr) { - pud_clear(level3p++); - addr += PUD_SIZE; - } -out: - return result; -} - - -static int init_level4_page(struct kimage *image, pgd_t *level4p, - unsigned long addr, unsigned long last_addr) -{ - unsigned long end_addr; - int result; - - result = 0; - addr &= PAGE_MASK; - end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE); - while ((addr < last_addr) && (addr < end_addr)) { - struct page *page; - pud_t *level3p; - - page = kimage_alloc_control_pages(image, 0); - if (!page) { - result = -ENOMEM; - goto out; - } - level3p = (pud_t *)page_address(page); - result = init_level3_page(image, level3p, addr, last_addr); - if (result) - goto out; - set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE)); - addr += PGDIR_SIZE; - } - /* clear the unused entries */ - while (addr < end_addr) { - pgd_clear(level4p++); - addr += PGDIR_SIZE; - } -out: - return result; -} - static void free_transition_pgtable(struct kimage *image) { free_page((unsigned long)image->arch.pud); @@ -203,15 +71,37 @@ err: return result; } +static void *alloc_pgt_page(void *data) +{ + struct kimage *image = (struct kimage *)data; + struct page *page; + void *p = NULL; + + page = kimage_alloc_control_pages(image, 0); + if (page) { + p = page_address(page); + clear_page(p); + } + + return p; +} + static int init_pgtable(struct kimage *image, unsigned long start_pgtable) { + struct x86_mapping_info info = { + .alloc_pgt_page = alloc_pgt_page, + .context = image, + .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, + }; unsigned long mstart, mend; pgd_t *level4p; int result; int i; level4p = (pgd_t *)__va(start_pgtable); - result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); + clear_page(level4p); + result = kernel_ident_mapping_init(&info, level4p, + 0, max_pfn << PAGE_SHIFT); if (result) return result; @@ -225,7 +115,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; - result = ident_mapping_init(image, level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, + level4p, mstart, mend); if (result) return result; -- cgit v1.2.2 From 0e691cf824f76adefb4498fe39c300aba2c2575a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:05 -0800 Subject: x86, kexec, 64bit: Only set ident mapping for ram. We should set mappings only for usable memory ranges under max_pfn Otherwise causes same problem that is fixed by x86, mm: Only direct map addresses that are marked as E820_RAM This patch exposes pfn_mapped array, and only sets ident mapping for ranges in that array. This patch relies on new kernel_ident_mapping_init that could handle existing pgd/pud between different calls. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-25-git-send-email-yinghai@kernel.org Cc: Alexander Duyck Signed-off-by: H. Peter Anvin --- arch/x86/kernel/machine_kexec_64.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index d2d7e023a8c8..4eabc160696f 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -100,10 +100,15 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) level4p = (pgd_t *)__va(start_pgtable); clear_page(level4p); - result = kernel_ident_mapping_init(&info, level4p, - 0, max_pfn << PAGE_SHIFT); - if (result) - return result; + for (i = 0; i < nr_pfn_mapped; i++) { + mstart = pfn_mapped[i].start << PAGE_SHIFT; + mend = pfn_mapped[i].end << PAGE_SHIFT; + + result = kernel_ident_mapping_init(&info, + level4p, mstart, mend); + if (result) + return result; + } /* * segments's mem ranges could be outside 0 ~ max_pfn, -- cgit v1.2.2 From ee92d815027a76ef92f3ec7b155b0c8aa345f239 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 28 Jan 2013 20:16:44 -0800 Subject: x86, boot: Support loading bzImage, boot_params and ramdisk above 4G xloadflags bit 1 indicates that we can load the kernel and all data structures above 4G; it is set if kernel is relocatable and 64bit. bootloader will check if xloadflags bit 1 is set to decide if it could load ramdisk and kernel high above 4G. bootloader will fill value to ext_ramdisk_image/size for high 32bits when it load ramdisk above 4G. kernel use get_ramdisk_image/size to use ext_ramdisk_image/size to get right positon for ramdisk. Signed-off-by: Yinghai Lu Cc: Rob Landley Cc: Matt Fleming Cc: Gokul Caushik Cc: Josh Triplett Cc: Joe Millenbach Link: http://lkml.kernel.org/r/1359058816-7615-26-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 2 ++ arch/x86/kernel/setup.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 62c8ce44cac4..6873b070d72c 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -116,6 +116,8 @@ static unsigned long get_cmd_line_ptr(void) { unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr; + cmd_line_ptr |= (u64)boot_params.ext_cmd_line_ptr << 32; + return cmd_line_ptr; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 83b38617ff59..519f2bc4950a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -298,12 +298,16 @@ static u64 __init get_ramdisk_image(void) { u64 ramdisk_image = boot_params.hdr.ramdisk_image; + ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32; + return ramdisk_image; } static u64 __init get_ramdisk_size(void) { u64 ramdisk_size = boot_params.hdr.ramdisk_size; + ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32; + return ramdisk_size; } -- cgit v1.2.2 From d1af6d045fba6b070fa81f54dfe9227214be99ea Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:08 -0800 Subject: x86, boot: Not need to check setup_header version for setup_data That is for bootloaders. setup_data is in setup_header, and bootloader is copying that from bzImage. So for old bootloader should keep that as 0 already. old kexec-tools till now for elf image set setup_data to 0, so it is ok. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-28-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 519f2bc4950a..b80bee10982f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -439,8 +439,6 @@ static void __init parse_setup_data(void) struct setup_data *data; u64 pa_data; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { u32 data_len, map_len; @@ -476,8 +474,6 @@ static void __init e820_reserve_setup_data(void) u64 pa_data; int found = 0; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); @@ -501,8 +497,6 @@ static void __init memblock_x86_reserve_range_setup_data(void) struct setup_data *data; u64 pa_data; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); -- cgit v1.2.2 From 595ad9af8584908ea5fb698b836169d05b99f186 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:09 -0800 Subject: memblock: Add memblock_mem_size() Use it to get mem size under the limit_pfn. to replace local version in x86 reserved_initrd. -v2: remove not needed cast that is pointed out by HPA. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-29-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b80bee10982f..bbe8cdf7515e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -363,20 +363,6 @@ static void __init relocate_initrd(void) ramdisk_here, ramdisk_here + ramdisk_size - 1); } -static u64 __init get_mem_size(unsigned long limit_pfn) -{ - int i; - u64 mapped_pages = 0; - unsigned long start_pfn, end_pfn; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min_t(unsigned long, start_pfn, limit_pfn); - end_pfn = min_t(unsigned long, end_pfn, limit_pfn); - mapped_pages += end_pfn - start_pfn; - } - - return mapped_pages << PAGE_SHIFT; -} static void __init early_reserve_initrd(void) { /* Assume only end is not page aligned */ @@ -404,7 +390,7 @@ static void __init reserve_initrd(void) initrd_start = 0; - mapped_size = get_mem_size(max_pfn_mapped); + mapped_size = memblock_mem_size(max_pfn_mapped); if (ramdisk_size >= (mapped_size>>1)) panic("initrd too large to handle, " "disabling initrd (%lld needed, %lld available)\n", -- cgit v1.2.2 From 7d41a8a4a2b2438621a9159477bff36a11d79a42 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:10 -0800 Subject: x86, kdump: Remove crashkernel range find limit for 64bit Now kexeced kernel/ramdisk could be above 4g, so remove 896 limit for 64bit. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-30-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bbe8cdf7515e..4778ddeedc8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -501,13 +501,11 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. - * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this - * limit once kexec-tools are fixed. */ #ifdef CONFIG_X86_32 # define CRASH_KERNEL_ADDR_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX (896 << 20) +# define CRASH_KERNEL_ADDR_MAX MAXMEM #endif static void __init reserve_crashkernel(void) -- cgit v1.2.2 From 0212f9159694be61c6bc52e925fa76643e0c1abf Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:11 -0800 Subject: x86: Add Crash kernel low reservation During kdump kernel's booting stage, it need to find low ram for swiotlb buffer when system does not support intel iommu/dmar remapping. kexed-tools is appending memmap=exactmap and range from /proc/iomem with "Crash kernel", and that range is above 4G for 64bit after boot protocol 2.12. We need to add another range in /proc/iomem like "Crash kernel low", so kexec-tools could find that info and append to kdump kernel command line. Try to reserve some under 4G if the normal "Crash kernel" is above 4G. User could specify the size with crashkernel_low=XX[KMG]. -v2: fix warning that is found by Fengguang's test robot. -v3: move out get_mem_size change to another patch, to solve compiling warning that is found by Borislav Petkov -v4: user must specify crashkernel_low if system does not support intel or amd iommu. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-31-git-send-email-yinghai@kernel.org Cc: Eric Biederman Cc: Rob Landley Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 42 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4778ddeedc8a..5dc47c3e537b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -508,8 +508,44 @@ static void __init memblock_x86_reserve_range_setup_data(void) # define CRASH_KERNEL_ADDR_MAX MAXMEM #endif +static void __init reserve_crashkernel_low(void) +{ +#ifdef CONFIG_X86_64 + const unsigned long long alignment = 16<<20; /* 16M */ + unsigned long long low_base = 0, low_size = 0; + unsigned long total_low_mem; + unsigned long long base; + int ret; + + total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + ret = parse_crashkernel_low(boot_command_line, total_low_mem, + &low_size, &base); + if (ret != 0 || low_size <= 0) + return; + + low_base = memblock_find_in_range(low_size, (1ULL<<32), + low_size, alignment); + + if (!low_base) { + pr_info("crashkernel low reservation failed - No suitable area found.\n"); + + return; + } + + memblock_reserve(low_base, low_size); + pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n", + (unsigned long)(low_size >> 20), + (unsigned long)(low_base >> 20), + (unsigned long)(total_low_mem >> 20)); + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + insert_resource(&iomem_resource, &crashk_low_res); +#endif +} + static void __init reserve_crashkernel(void) { + const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; int ret; @@ -523,8 +559,6 @@ static void __init reserve_crashkernel(void) /* 0 means: find the address automatically */ if (crash_base <= 0) { - const unsigned long long alignment = 16<<20; /* 16M */ - /* * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ @@ -535,6 +569,7 @@ static void __init reserve_crashkernel(void) pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } + } else { unsigned long long start; @@ -556,6 +591,9 @@ static void __init reserve_crashkernel(void) crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; insert_resource(&iomem_resource, &crashk_res); + + if (crash_base >= (1ULL<<32)) + reserve_crashkernel_low(); } #else static void __init reserve_crashkernel(void) -- cgit v1.2.2 From 6c902b656c4a808d9c6f40a387b166455efecd62 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:12 -0800 Subject: x86: Merge early kernel reserve for 32bit and 64bit They are the same, and we could move them out from head32/64.c to setup.c. We are using memblock, and it could handle overlapping properly, so we don't need to reserve some at first to hold the location, and just need to make sure we reserve them before we are using memblock to find free mem to use. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-32-git-send-email-yinghai@kernel.org Cc: Alexander Duyck Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head32.c | 9 --------- arch/x86/kernel/head64.c | 9 --------- arch/x86/kernel/setup.c | 9 +++++++++ 3 files changed, 9 insertions(+), 18 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index a795b54de7d3..138463a24877 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -33,9 +33,6 @@ void __init i386_start_kernel(void) { sanitize_boot_params(&boot_params); - memblock_reserve(__pa_symbol(&_text), - __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); - /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_MRST: @@ -49,11 +46,5 @@ void __init i386_start_kernel(void) break; } - /* - * At this point everything still needed from the boot loader - * or BIOS or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - start_kernel(); } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6873b070d72c..57334f4cd3af 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -186,16 +186,7 @@ void __init x86_64_start_reservations(char *real_mode_data) if (!boot_params.hdr.version) copy_bootdata(__va(real_mode_data)); - memblock_reserve(__pa_symbol(&_text), - __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); - reserve_ebda_region(); - /* - * At this point everything still needed from the boot loader - * or BIOS or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - start_kernel(); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5dc47c3e537b..a74701af74e3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -805,8 +805,17 @@ early_param("reservelow", parse_reservelow); void __init setup_arch(char **cmdline_p) { + memblock_reserve(__pa_symbol(_text), + (unsigned long)__bss_stop - (unsigned long)_text); + early_reserve_initrd(); + /* + * At this point everything still needed from the boot loader + * or BIOS or kernel text should be early reserved or marked not + * RAM in e820. All other memory is free game. + */ + #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); -- cgit v1.2.2 From 83e68189745ad931c2afd45d8ee3303929233e7f Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Wed, 14 Nov 2012 09:42:35 +0000 Subject: efi: Make 'efi_enabled' a function to query EFI facilities Originally 'efi_enabled' indicated whether a kernel was booted from EFI firmware. Over time its semantics have changed, and it now indicates whether or not we are booted on an EFI machine with bit-native firmware, e.g. 64-bit kernel with 64-bit firmware. The immediate motivation for this patch is the bug report at, https://bugs.launchpad.net/ubuntu-cdimage/+bug/1040557 which details how running a platform driver on an EFI machine that is designed to run under BIOS can cause the machine to become bricked. Also, the following report, https://bugzilla.kernel.org/show_bug.cgi?id=47121 details how running said driver can also cause Machine Check Exceptions. Drivers need a new means of detecting whether they're running on an EFI machine, as sadly the expression, if (!efi_enabled) hasn't been a sufficient condition for quite some time. Users actually want to query 'efi_enabled' for different reasons - what they really want access to is the list of available EFI facilities. For instance, the x86 reboot code needs to know whether it can invoke the ResetSystem() function provided by the EFI runtime services, while the ACPI OSL code wants to know whether the EFI config tables were mapped successfully. There are also checks in some of the platform driver code to simply see if they're running on an EFI machine (which would make it a bad idea to do BIOS-y things). This patch is a prereq for the samsung-laptop fix patch. Cc: David Airlie Cc: Corentin Chary Cc: Matthew Garrett Cc: Dave Jiang Cc: Olof Johansson Cc: Peter Jones Cc: Colin Ian King Cc: Steve Langasek Cc: Tony Luck Cc: Konrad Rzeszutek Wilk Cc: Rafael J. Wysocki Cc: Signed-off-by: Matt Fleming Signed-off-by: H. Peter Anvin --- arch/x86/kernel/reboot.c | 2 +- arch/x86/kernel/setup.c | 28 ++++++++++++++-------------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 4e8ba39eaf0f..76fa1e9a2b39 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -584,7 +584,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_EFI: - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 00f6c1472b85..8b24289cc10c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -807,15 +807,15 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - efi_enabled = 1; - efi_64bit = false; + set_bit(EFI_BOOT, &x86_efi_facility); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - efi_enabled = 1; - efi_64bit = true; + set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_64BIT, &x86_efi_facility); } - if (efi_enabled && efi_memblock_x86_reserve_range()) - efi_enabled = 0; + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); #endif x86_init.oem.arch_setup(); @@ -888,7 +888,7 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); - if (efi_enabled) + if (efi_enabled(EFI_BOOT)) efi_init(); dmi_scan_machine(); @@ -971,7 +971,7 @@ void __init setup_arch(char **cmdline_p) * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. */ - if (efi_enabled) + if (efi_enabled(EFI_MEMMAP)) efi_reserve_boot_services(); /* preallocate 4k for mptable mpc */ @@ -1114,7 +1114,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) conswitchp = &vga_con; #elif defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; @@ -1131,14 +1131,14 @@ void __init setup_arch(char **cmdline_p) register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI - /* Once setup is done above, disable efi_enabled on mismatched - * firmware/kernel archtectures since there is no support for - * runtime services. + /* Once setup is done above, unmap the EFI memory map on + * mismatched firmware/kernel archtectures since there is no + * support for runtime services. */ - if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) { + if (efi_enabled(EFI_BOOT) && + IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) { pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); - efi_enabled = 0; } #endif } -- cgit v1.2.2 From 2663960c159f23cbfb8e196c96e9fc9f3b5f1a8d Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Tue, 22 Jan 2013 22:24:23 -0800 Subject: perf: Make EVENT_ATTR global Rename EVENT_ATTR() to PMU_EVENT_ATTR() and make it global so it is available to all architectures. Further to allow architectures flexibility, have PMU_EVENT_ATTR() pass in the variable name as a parameter. Changelog[v2] - [Jiri Olsa] No need to define PMU_EVENT_PTR() Signed-off-by: Sukadev Bhattiprolu Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Anton Blanchard Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: linuxppc-dev@ozlabs.org Link: http://lkml.kernel.org/r/20130123062422.GC13720@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- arch/x86/kernel/cpu/perf_event.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 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 6774c17a5576..c0df5ed2e048 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1310,11 +1310,6 @@ static struct attribute_group x86_pmu_format_group = { .attrs = NULL, }; -struct perf_pmu_events_attr { - struct device_attribute attr; - u64 id; -}; - /* * Remove all undefined events (x86_pmu.event_map(id) == 0) * out of events_attr attributes. @@ -1348,11 +1343,9 @@ static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *at #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, \ -}; +#define EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id, \ + events_sysfs_show) EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); -- cgit v1.2.2 From 9cd4d78e21cfdc709b1af516214ec4f69ee0e6bd Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:22 -0800 Subject: x86/microcode_intel.h: Define functions and macros for early loading ucode Define some functions and macros that will be used in early loading ucode. Some of them are moved from microcode_intel.c driver in order to be called in early boot phase before module can be called. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-3-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/Makefile | 3 + arch/x86/kernel/microcode_core.c | 7 +- arch/x86/kernel/microcode_intel.c | 198 ++++++-------------------------------- 3 files changed, 37 insertions(+), 171 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 34e923a53762..052abee2740d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -88,6 +88,9 @@ obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o +obj-$(CONFIG_MICROCODE_EARLY) += microcode_core_early.o +obj-$(CONFIG_MICROCODE_INTEL_EARLY) += microcode_intel_early.o +obj-$(CONFIG_MICROCODE_INTEL_LIB) += microcode_intel_lib.o microcode-y := microcode_core.o microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 3a04b224d0c0..22db92bbdf1a 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -364,10 +364,7 @@ static struct attribute_group mc_attr_group = { static void microcode_fini_cpu(int cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - microcode_ops->microcode_fini_cpu(cpu); - uci->valid = 0; } static enum ucode_state microcode_resume_cpu(int cpu) @@ -383,6 +380,10 @@ static enum ucode_state microcode_resume_cpu(int cpu) static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) { enum ucode_state ustate; + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + if (uci && uci->valid) + return UCODE_OK; if (collect_cpu_info(cpu)) return UCODE_ERROR; diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 3544aed39338..5fb2cebf556b 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -79,7 +79,7 @@ #include #include -#include +#include #include #include @@ -87,59 +87,6 @@ MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian "); MODULE_LICENSE("GPL"); -struct microcode_header_intel { - unsigned int hdrver; - unsigned int rev; - unsigned int date; - unsigned int sig; - unsigned int cksum; - unsigned int ldrver; - unsigned int pf; - unsigned int datasize; - unsigned int totalsize; - unsigned int reserved[3]; -}; - -struct microcode_intel { - struct microcode_header_intel hdr; - unsigned int bits[0]; -}; - -/* microcode format is extended from prescott processors */ -struct extended_signature { - unsigned int sig; - unsigned int pf; - unsigned int cksum; -}; - -struct extended_sigtable { - unsigned int count; - unsigned int cksum; - unsigned int reserved[3]; - struct extended_signature sigs[0]; -}; - -#define DEFAULT_UCODE_DATASIZE (2000) -#define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) -#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) -#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) -#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) -#define DWSIZE (sizeof(u32)) - -#define get_totalsize(mc) \ - (((struct microcode_intel *)mc)->hdr.totalsize ? \ - ((struct microcode_intel *)mc)->hdr.totalsize : \ - DEFAULT_UCODE_TOTALSIZE) - -#define get_datasize(mc) \ - (((struct microcode_intel *)mc)->hdr.datasize ? \ - ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE) - -#define sigmatch(s1, s2, p1, p2) \ - (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0)))) - -#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) - static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu_num); @@ -162,128 +109,25 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) return 0; } -static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf) -{ - return (!sigmatch(sig, csig->sig, pf, csig->pf)) ? 0 : 1; -} - -static inline int -update_match_revision(struct microcode_header_intel *mc_header, int rev) -{ - return (mc_header->rev <= rev) ? 0 : 1; -} - -static int microcode_sanity_check(void *mc) -{ - unsigned long total_size, data_size, ext_table_size; - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header = NULL; - int sum, orig_sum, ext_sigcount = 0, i; - struct extended_signature *ext_sig; - - total_size = get_totalsize(mc_header); - data_size = get_datasize(mc_header); - - if (data_size + MC_HEADER_SIZE > total_size) { - pr_err("error! Bad data size in microcode data file\n"); - return -EINVAL; - } - - if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { - pr_err("error! Unknown microcode update format\n"); - return -EINVAL; - } - ext_table_size = total_size - (MC_HEADER_SIZE + data_size); - if (ext_table_size) { - if ((ext_table_size < EXT_HEADER_SIZE) - || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { - pr_err("error! Small exttable size in microcode data file\n"); - return -EINVAL; - } - ext_header = mc + MC_HEADER_SIZE + data_size; - if (ext_table_size != exttable_size(ext_header)) { - pr_err("error! Bad exttable size in microcode data file\n"); - return -EFAULT; - } - ext_sigcount = ext_header->count; - } - - /* check extended table checksum */ - if (ext_table_size) { - int ext_table_sum = 0; - int *ext_tablep = (int *)ext_header; - - i = ext_table_size / DWSIZE; - while (i--) - ext_table_sum += ext_tablep[i]; - if (ext_table_sum) { - pr_warning("aborting, bad extended signature table checksum\n"); - return -EINVAL; - } - } - - /* calculate the checksum */ - orig_sum = 0; - i = (MC_HEADER_SIZE + data_size) / DWSIZE; - while (i--) - orig_sum += ((int *)mc)[i]; - if (orig_sum) { - pr_err("aborting, bad checksum\n"); - return -EINVAL; - } - if (!ext_table_size) - return 0; - /* check extended signature checksum */ - for (i = 0; i < ext_sigcount; i++) { - ext_sig = (void *)ext_header + EXT_HEADER_SIZE + - EXT_SIGNATURE_SIZE * i; - sum = orig_sum - - (mc_header->sig + mc_header->pf + mc_header->cksum) - + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); - if (sum) { - pr_err("aborting, bad checksum\n"); - return -EINVAL; - } - } - return 0; -} - /* * return 0 - no update found * return 1 - found update */ -static int -get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev) +static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) { - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - int ext_sigcount, i; - struct extended_signature *ext_sig; - - if (!update_match_revision(mc_header, rev)) - return 0; - - if (update_match_cpu(cpu_sig, mc_header->sig, mc_header->pf)) - return 1; + struct cpu_signature cpu_sig; + unsigned int csig, cpf, crev; - /* Look for ext. headers: */ - if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) - return 0; + collect_cpu_info(cpu, &cpu_sig); - ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + csig = cpu_sig.sig; + cpf = cpu_sig.pf; + crev = cpu_sig.rev; - for (i = 0; i < ext_sigcount; i++) { - if (update_match_cpu(cpu_sig, ext_sig->sig, ext_sig->pf)) - return 1; - ext_sig++; - } - return 0; + return get_matching_microcode(csig, cpf, mc_intel, crev); } -static int apply_microcode(int cpu) +int apply_microcode(int cpu) { struct microcode_intel *mc_intel; struct ucode_cpu_info *uci; @@ -300,6 +144,14 @@ static int apply_microcode(int cpu) if (mc_intel == NULL) return 0; + /* + * Microcode on this CPU could be updated earlier. Only apply the + * microcode patch in mc_intel when it is newer than the one on this + * CPU. + */ + if (get_matching_mc(mc_intel, cpu) == 0) + return 0; + /* write microcode via MSR 0x79 */ wrmsr(MSR_IA32_UCODE_WRITE, (unsigned long) mc_intel->bits, @@ -338,6 +190,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, unsigned int leftover = size; enum ucode_state state = UCODE_OK; unsigned int curr_mc_size = 0; + unsigned int csig, cpf; while (leftover) { struct microcode_header_intel mc_header; @@ -362,11 +215,13 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, } if (get_ucode_data(mc, ucode_ptr, mc_size) || - microcode_sanity_check(mc) < 0) { + microcode_sanity_check(mc, 1) < 0) { break; } - if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) { + csig = uci->cpu_sig.sig; + cpf = uci->cpu_sig.pf; + if (get_matching_microcode(csig, cpf, mc, new_rev)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; @@ -393,6 +248,13 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(uci->mc); uci->mc = (struct microcode_intel *)new_mc; + /* + * If early loading microcode is supported, save this mc into + * permanent memory. So it will be loaded early when a CPU is hot added + * or resumes. + */ + save_mc_for_early(new_mc); + pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); out: -- cgit v1.2.2 From d288e1cf8e62f3e4034f1f021f047009c4ac0b3c Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:23 -0800 Subject: x86/common.c: Make have_cpuid_p() a global function Remove static declaration in have_cpuid_p() to make it a global function. The function will be called in early loading microcode. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-4-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9c3ab43a6954..d7fd2468752a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -37,6 +37,8 @@ #include #include #include +#include +#include #ifdef CONFIG_X86_LOCAL_APIC #include @@ -213,7 +215,7 @@ static inline int flag_is_changeable_p(u32 flag) } /* Probe for the CPUID instruction */ -static int __cpuinit have_cpuid_p(void) +int __cpuinit have_cpuid_p(void) { return flag_is_changeable_p(X86_EFLAGS_ID); } @@ -249,11 +251,6 @@ static inline int flag_is_changeable_p(u32 flag) { return 1; } -/* Probe for the CPUID instruction */ -static inline int have_cpuid_p(void) -{ - return 1; -} static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) { } -- cgit v1.2.2 From e6ebf5deaaaa33b661f0db86380c232b162bd68c Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:24 -0800 Subject: x86/common.c: load ucode in 64 bit or show loading ucode info in 32 bit on AP In 64 bit, load ucode on AP in cpu_init(). In 32 bit, show ucode loading info on AP in cpu_init(). Microcode has been loaded earlier before paging. Now it is safe to show the loading microcode info on this AP. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-5-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d7fd2468752a..d814772c5bed 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1220,6 +1220,12 @@ void __cpuinit cpu_init(void) int cpu; int i; + /* + * Load microcode on this cpu if a valid microcode is available. + * This is early microcode loading procedure. + */ + load_ucode_ap(); + cpu = stack_smp_processor_id(); t = &per_cpu(init_tss, cpu); oist = &per_cpu(orig_ist, cpu); @@ -1311,6 +1317,8 @@ void __cpuinit cpu_init(void) struct tss_struct *t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; + show_ucode_info_early(); + if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); for (;;) -- cgit v1.2.2 From a8ebf6d1d6971b90a20f5bd0465e6d520377e33b Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:25 -0800 Subject: x86/microcode_core_early.c: Define interfaces for early loading ucode Define interfaces load_ucode_bsp() and load_ucode_ap() to load ucode on BSP and AP in early boot time. These are generic interfaces. Internally they call vendor specific implementations. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-6-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/microcode_core_early.c | 76 ++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 arch/x86/kernel/microcode_core_early.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c new file mode 100644 index 000000000000..577db8417d15 --- /dev/null +++ b/arch/x86/kernel/microcode_core_early.c @@ -0,0 +1,76 @@ +/* + * X86 CPU microcode early update for Linux + * + * Copyright (C) 2012 Fenghua Yu + * H Peter Anvin" + * + * This driver allows to early upgrade microcode on Intel processors + * belonging to IA-32 family - PentiumPro, Pentium II, + * Pentium III, Xeon, Pentium 4, etc. + * + * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture + * Software Developer's Manual. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) +#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') +#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I') +#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l') +#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h') +#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i') +#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D') + +#define CPUID_IS(a, b, c, ebx, ecx, edx) \ + (!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c)))) + +/* + * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. + * x86_vendor() gets vendor id for BSP. + * + * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify + * coding, we still use x86_vendor() to get vendor id for AP. + * + * x86_vendor() gets vendor information directly through cpuid. + */ +static int __cpuinit x86_vendor(void) +{ + u32 eax = 0x00000000; + u32 ebx, ecx = 0, edx; + + if (!have_cpuid_p()) + return X86_VENDOR_UNKNOWN; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) + return X86_VENDOR_INTEL; + + if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx)) + return X86_VENDOR_AMD; + + return X86_VENDOR_UNKNOWN; +} + +void __init load_ucode_bsp(void) +{ + int vendor = x86_vendor(); + + if (vendor == X86_VENDOR_INTEL) + load_ucode_intel_bsp(); +} + +void __cpuinit load_ucode_ap(void) +{ + int vendor = x86_vendor(); + + if (vendor == X86_VENDOR_INTEL) + load_ucode_intel_ap(); +} -- cgit v1.2.2 From e666dfa273db1b12711eaec91facac5fec2ec851 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:26 -0800 Subject: x86/microcode_intel_lib.c: Early update ucode on Intel's CPU Define interfaces microcode_sanity_check() and get_matching_microcode(). They are called both in early boot time and in microcode Intel driver. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-7-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/microcode_intel_lib.c | 174 ++++++++++++++++++++++++++++++++++ 1 file changed, 174 insertions(+) create mode 100644 arch/x86/kernel/microcode_intel_lib.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/microcode_intel_lib.c b/arch/x86/kernel/microcode_intel_lib.c new file mode 100644 index 000000000000..ce69320d0179 --- /dev/null +++ b/arch/x86/kernel/microcode_intel_lib.c @@ -0,0 +1,174 @@ +/* + * Intel CPU Microcode Update Driver for Linux + * + * Copyright (C) 2012 Fenghua Yu + * H Peter Anvin" + * + * This driver allows to upgrade microcode on Intel processors + * belonging to IA-32 family - PentiumPro, Pentium II, + * Pentium III, Xeon, Pentium 4, etc. + * + * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture + * Software Developer's Manual + * Order Number 253668 or free download from: + * + * http://developer.intel.com/Assets/PDF/manual/253668.pdf + * + * For more information, go to http://www.urbanmyth.org/microcode + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include +#include +#include +#include + +#include +#include +#include + +static inline int +update_match_cpu(unsigned int csig, unsigned int cpf, + unsigned int sig, unsigned int pf) +{ + return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; +} + +int +update_match_revision(struct microcode_header_intel *mc_header, int rev) +{ + return (mc_header->rev <= rev) ? 0 : 1; +} + +int microcode_sanity_check(void *mc, int print_err) +{ + unsigned long total_size, data_size, ext_table_size; + struct microcode_header_intel *mc_header = mc; + struct extended_sigtable *ext_header = NULL; + int sum, orig_sum, ext_sigcount = 0, i; + struct extended_signature *ext_sig; + + total_size = get_totalsize(mc_header); + data_size = get_datasize(mc_header); + + if (data_size + MC_HEADER_SIZE > total_size) { + if (print_err) + pr_err("error! Bad data size in microcode data file\n"); + return -EINVAL; + } + + if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { + if (print_err) + pr_err("error! Unknown microcode update format\n"); + return -EINVAL; + } + ext_table_size = total_size - (MC_HEADER_SIZE + data_size); + if (ext_table_size) { + if ((ext_table_size < EXT_HEADER_SIZE) + || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { + if (print_err) + pr_err("error! Small exttable size in microcode data file\n"); + return -EINVAL; + } + ext_header = mc + MC_HEADER_SIZE + data_size; + if (ext_table_size != exttable_size(ext_header)) { + if (print_err) + pr_err("error! Bad exttable size in microcode data file\n"); + return -EFAULT; + } + ext_sigcount = ext_header->count; + } + + /* check extended table checksum */ + if (ext_table_size) { + int ext_table_sum = 0; + int *ext_tablep = (int *)ext_header; + + i = ext_table_size / DWSIZE; + while (i--) + ext_table_sum += ext_tablep[i]; + if (ext_table_sum) { + if (print_err) + pr_warn("aborting, bad extended signature table checksum\n"); + return -EINVAL; + } + } + + /* calculate the checksum */ + orig_sum = 0; + i = (MC_HEADER_SIZE + data_size) / DWSIZE; + while (i--) + orig_sum += ((int *)mc)[i]; + if (orig_sum) { + if (print_err) + pr_err("aborting, bad checksum\n"); + return -EINVAL; + } + if (!ext_table_size) + return 0; + /* check extended signature checksum */ + for (i = 0; i < ext_sigcount; i++) { + ext_sig = (void *)ext_header + EXT_HEADER_SIZE + + EXT_SIGNATURE_SIZE * i; + sum = orig_sum + - (mc_header->sig + mc_header->pf + mc_header->cksum) + + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); + if (sum) { + if (print_err) + pr_err("aborting, bad checksum\n"); + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL_GPL(microcode_sanity_check); + +/* + * return 0 - no update found + * return 1 - found update + */ +int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev) +{ + struct microcode_header_intel *mc_header = mc; + struct extended_sigtable *ext_header; + unsigned long total_size = get_totalsize(mc_header); + int ext_sigcount, i; + struct extended_signature *ext_sig; + + if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf)) + return 1; + + /* Look for ext. headers: */ + if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + return 0; + + ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; + ext_sigcount = ext_header->count; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + + for (i = 0; i < ext_sigcount; i++) { + if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf)) + return 1; + ext_sig++; + } + return 0; +} + +/* + * return 0 - no update found + * return 1 - found update + */ +int get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev) +{ + struct microcode_header_intel *mc_header = mc; + + if (!update_match_revision(mc_header, rev)) + return 0; + + return get_matching_sig(csig, cpf, mc, rev); +} +EXPORT_SYMBOL_GPL(get_matching_microcode); -- cgit v1.2.2 From ec400ddeff200b068ddc6c70f7321f49ecf32ed5 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:28 -0800 Subject: x86/microcode_intel_early.c: Early update ucode on Intel's CPU Implementation of early update ucode on Intel's CPU. load_ucode_intel_bsp() scans ucode in initrd image file which is a cpio format ucode followed by ordinary initrd image file. The binary ucode file is stored in kernel/x86/microcode/GenuineIntel.bin in the cpio data. All ucode patches with the same model as BSP are saved in memory. A matching ucode patch is updated on BSP. load_ucode_intel_ap() reads saved ucoded patches and updates ucode on AP. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-9-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/microcode_intel_early.c | 796 ++++++++++++++++++++++++++++++++ 1 file changed, 796 insertions(+) create mode 100644 arch/x86/kernel/microcode_intel_early.c (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c new file mode 100644 index 000000000000..7890bc838952 --- /dev/null +++ b/arch/x86/kernel/microcode_intel_early.c @@ -0,0 +1,796 @@ +/* + * Intel CPU microcode early update for Linux + * + * Copyright (C) 2012 Fenghua Yu + * H Peter Anvin" + * + * This allows to early upgrade microcode on Intel processors + * belonging to IA-32 family - PentiumPro, Pentium II, + * Pentium III, Xeon, Pentium 4, etc. + * + * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture + * Software Developer's Manual. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +struct mc_saved_data { + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; +} mc_saved_data; + +static enum ucode_state __cpuinit +generic_load_microcode_early(struct microcode_intel **mc_saved_p, + unsigned int mc_saved_count, + struct ucode_cpu_info *uci) +{ + struct microcode_intel *ucode_ptr, *new_mc = NULL; + int new_rev = uci->cpu_sig.rev; + enum ucode_state state = UCODE_OK; + unsigned int mc_size; + struct microcode_header_intel *mc_header; + unsigned int csig = uci->cpu_sig.sig; + unsigned int cpf = uci->cpu_sig.pf; + int i; + + for (i = 0; i < mc_saved_count; i++) { + ucode_ptr = mc_saved_p[i]; + + mc_header = (struct microcode_header_intel *)ucode_ptr; + mc_size = get_totalsize(mc_header); + if (get_matching_microcode(csig, cpf, ucode_ptr, new_rev)) { + new_rev = mc_header->rev; + new_mc = ucode_ptr; + } + } + + if (!new_mc) { + state = UCODE_NFOUND; + goto out; + } + + uci->mc = (struct microcode_intel *)new_mc; +out: + return state; +} + +static void __cpuinit +microcode_pointer(struct microcode_intel **mc_saved, + unsigned long *mc_saved_in_initrd, + unsigned long initrd_start, int mc_saved_count) +{ + int i; + + for (i = 0; i < mc_saved_count; i++) + mc_saved[i] = (struct microcode_intel *) + (mc_saved_in_initrd[i] + initrd_start); +} + +#ifdef CONFIG_X86_32 +static void __cpuinit +microcode_phys(struct microcode_intel **mc_saved_tmp, + struct mc_saved_data *mc_saved_data) +{ + int i; + struct microcode_intel ***mc_saved; + + mc_saved = (struct microcode_intel ***) + __pa_symbol(&mc_saved_data->mc_saved); + for (i = 0; i < mc_saved_data->mc_saved_count; i++) { + struct microcode_intel *p; + + p = *(struct microcode_intel **) + __pa(mc_saved_data->mc_saved + i); + mc_saved_tmp[i] = (struct microcode_intel *)__pa(p); + } +} +#endif + +static enum ucode_state __cpuinit +load_microcode(struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + unsigned long initrd_start, + struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int count = mc_saved_data->mc_saved_count; + + if (!mc_saved_data->mc_saved) { + microcode_pointer(mc_saved_tmp, mc_saved_in_initrd, + initrd_start, count); + + return generic_load_microcode_early(mc_saved_tmp, count, uci); + } else { +#ifdef CONFIG_X86_32 + microcode_phys(mc_saved_tmp, mc_saved_data); + return generic_load_microcode_early(mc_saved_tmp, count, uci); +#else + return generic_load_microcode_early(mc_saved_data->mc_saved, + count, uci); +#endif + } +} + +static u8 get_x86_family(unsigned long sig) +{ + u8 x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} + +static u8 get_x86_model(unsigned long sig) +{ + u8 x86, x86_model; + + x86 = get_x86_family(sig); + x86_model = (sig >> 4) & 0xf; + + if (x86 == 0x6 || x86 == 0xf) + x86_model += ((sig >> 16) & 0xf) << 4; + + return x86_model; +} + +/* + * Given CPU signature and a microcode patch, this function finds if the + * microcode patch has matching family and model with the CPU. + */ +static enum ucode_state +matching_model_microcode(struct microcode_header_intel *mc_header, + unsigned long sig) +{ + u8 x86, x86_model; + u8 x86_ucode, x86_model_ucode; + struct extended_sigtable *ext_header; + unsigned long total_size = get_totalsize(mc_header); + unsigned long data_size = get_datasize(mc_header); + int ext_sigcount, i; + struct extended_signature *ext_sig; + + x86 = get_x86_family(sig); + x86_model = get_x86_model(sig); + + x86_ucode = get_x86_family(mc_header->sig); + x86_model_ucode = get_x86_model(mc_header->sig); + + if (x86 == x86_ucode && x86_model == x86_model_ucode) + return UCODE_OK; + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + return UCODE_NFOUND; + + ext_header = (struct extended_sigtable *) + mc_header + data_size + MC_HEADER_SIZE; + ext_sigcount = ext_header->count; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + + for (i = 0; i < ext_sigcount; i++) { + x86_ucode = get_x86_family(ext_sig->sig); + x86_model_ucode = get_x86_model(ext_sig->sig); + + if (x86 == x86_ucode && x86_model == x86_model_ucode) + return UCODE_OK; + + ext_sig++; + } + + return UCODE_NFOUND; +} + +static int +save_microcode(struct mc_saved_data *mc_saved_data, + struct microcode_intel **mc_saved_src, + unsigned int mc_saved_count) +{ + int i, j; + struct microcode_intel **mc_saved_p; + int ret; + + if (!mc_saved_count) + return -EINVAL; + + /* + * Copy new microcode data. + */ + mc_saved_p = kmalloc(mc_saved_count*sizeof(struct microcode_intel *), + GFP_KERNEL); + if (!mc_saved_p) + return -ENOMEM; + + for (i = 0; i < mc_saved_count; i++) { + struct microcode_intel *mc = mc_saved_src[i]; + struct microcode_header_intel *mc_header = &mc->hdr; + unsigned long mc_size = get_totalsize(mc_header); + mc_saved_p[i] = kmalloc(mc_size, GFP_KERNEL); + if (!mc_saved_p[i]) { + ret = -ENOMEM; + goto err; + } + if (!mc_saved_src[i]) { + ret = -EINVAL; + goto err; + } + memcpy(mc_saved_p[i], mc, mc_size); + } + + /* + * Point to newly saved microcode. + */ + mc_saved_data->mc_saved = mc_saved_p; + mc_saved_data->mc_saved_count = mc_saved_count; + + return 0; + +err: + for (j = 0; j <= i; j++) + kfree(mc_saved_p[j]); + kfree(mc_saved_p); + + return ret; +} + +/* + * A microcode patch in ucode_ptr is saved into mc_saved + * - if it has matching signature and newer revision compared to an existing + * patch mc_saved. + * - or if it is a newly discovered microcode patch. + * + * The microcode patch should have matching model with CPU. + */ +static void _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr, + unsigned int *mc_saved_count_p) +{ + int i; + int found = 0; + unsigned int mc_saved_count = *mc_saved_count_p; + struct microcode_header_intel *mc_header; + + mc_header = (struct microcode_header_intel *)ucode_ptr; + for (i = 0; i < mc_saved_count; i++) { + unsigned int sig, pf; + unsigned int new_rev; + struct microcode_header_intel *mc_saved_header = + (struct microcode_header_intel *)mc_saved[i]; + sig = mc_saved_header->sig; + pf = mc_saved_header->pf; + new_rev = mc_header->rev; + + if (get_matching_sig(sig, pf, ucode_ptr, new_rev)) { + found = 1; + if (update_match_revision(mc_header, new_rev)) { + /* + * Found an older ucode saved before. + * Replace the older one with this newer + * one. + */ + mc_saved[i] = + (struct microcode_intel *)ucode_ptr; + break; + } + } + } + if (i >= mc_saved_count && !found) + /* + * This ucode is first time discovered in ucode file. + * Save it to memory. + */ + mc_saved[mc_saved_count++] = + (struct microcode_intel *)ucode_ptr; + + *mc_saved_count_p = mc_saved_count; +} + +/* + * Get microcode matching with BSP's model. Only CPUs with the same model as + * BSP can stay in the platform. + */ +static enum ucode_state __init +get_matching_model_microcode(int cpu, unsigned long start, + void *data, size_t size, + struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + struct ucode_cpu_info *uci) +{ + u8 *ucode_ptr = data; + unsigned int leftover = size; + enum ucode_state state = UCODE_OK; + unsigned int mc_size; + struct microcode_header_intel *mc_header; + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count = mc_saved_data->mc_saved_count; + int i; + + while (leftover) { + mc_header = (struct microcode_header_intel *)ucode_ptr; + + mc_size = get_totalsize(mc_header); + if (!mc_size || mc_size > leftover || + microcode_sanity_check(ucode_ptr, 0) < 0) + break; + + leftover -= mc_size; + + /* + * Since APs with same family and model as the BSP may boot in + * the platform, we need to find and save microcode patches + * with the same family and model as the BSP. + */ + if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != + UCODE_OK) { + ucode_ptr += mc_size; + continue; + } + + _save_mc(mc_saved_tmp, ucode_ptr, &mc_saved_count); + + ucode_ptr += mc_size; + } + + if (leftover) { + state = UCODE_ERROR; + goto out; + } + + if (mc_saved_count == 0) { + state = UCODE_NFOUND; + goto out; + } + + for (i = 0; i < mc_saved_count; i++) + mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; + + mc_saved_data->mc_saved_count = mc_saved_count; +out: + return state; +} + +#define native_rdmsr(msr, val1, val2) \ +do { \ + u64 __val = native_read_msr((msr)); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ +} while (0) + +#define native_wrmsr(msr, low, high) \ + native_write_msr(msr, low, high); + +static int __cpuinit collect_cpu_info_early(struct ucode_cpu_info *uci) +{ + unsigned int val[2]; + u8 x86, x86_model; + struct cpu_signature csig; + unsigned int eax, ebx, ecx, edx; + + csig.sig = 0; + csig.pf = 0; + csig.rev = 0; + + memset(uci, 0, sizeof(*uci)); + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + csig.sig = eax; + + x86 = get_x86_family(csig.sig); + x86_model = get_x86_model(csig.sig); + + if ((x86_model >= 5) || (x86 > 6)) { + /* get processor flags from MSR 0x17 */ + native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + csig.pf = 1 << ((val[1] >> 18) & 7); + } + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + + csig.rev = val[1]; + + uci->cpu_sig = csig; + uci->valid = 1; + + return 0; +} + +#ifdef DEBUG +static void __ref show_saved_mc(void) +{ + int i, j; + unsigned int sig, pf, rev, total_size, data_size, date; + struct ucode_cpu_info uci; + + if (mc_saved_data.mc_saved_count == 0) { + pr_debug("no micorcode data saved.\n"); + return; + } + pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); + + collect_cpu_info_early(&uci); + + sig = uci.cpu_sig.sig; + pf = uci.cpu_sig.pf; + rev = uci.cpu_sig.rev; + pr_debug("CPU%d: sig=0x%x, pf=0x%x, rev=0x%x\n", + smp_processor_id(), sig, pf, rev); + + for (i = 0; i < mc_saved_data.mc_saved_count; i++) { + struct microcode_header_intel *mc_saved_header; + struct extended_sigtable *ext_header; + int ext_sigcount; + struct extended_signature *ext_sig; + + mc_saved_header = (struct microcode_header_intel *) + mc_saved_data.mc_saved[i]; + sig = mc_saved_header->sig; + pf = mc_saved_header->pf; + rev = mc_saved_header->rev; + total_size = get_totalsize(mc_saved_header); + data_size = get_datasize(mc_saved_header); + date = mc_saved_header->date; + + pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n", + i, sig, pf, rev, total_size, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + continue; + + ext_header = (struct extended_sigtable *) + mc_saved_header + data_size + MC_HEADER_SIZE; + ext_sigcount = ext_header->count; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + + for (j = 0; j < ext_sigcount; j++) { + sig = ext_sig->sig; + pf = ext_sig->pf; + + pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", + j, sig, pf); + + ext_sig++; + } + + } +} +#else +static inline void show_saved_mc(void) +{ +} +#endif + +#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +/* + * Save this mc into mc_saved_data. So it will be loaded early when a CPU is + * hot added or resumes. + * + * Please make sure this mc should be a valid microcode patch before calling + * this function. + */ +int save_mc_for_early(u8 *mc) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count_init; + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; + int ret = 0; + int i; + + /* + * Hold hotplug lock so mc_saved_data is not accessed by a CPU in + * hotplug. + */ + cpu_hotplug_driver_lock(); + + mc_saved_count_init = mc_saved_data.mc_saved_count; + mc_saved_count = mc_saved_data.mc_saved_count; + mc_saved = mc_saved_data.mc_saved; + + if (mc_saved && mc_saved_count) + memcpy(mc_saved_tmp, mc_saved, + mc_saved_count * sizeof(struct mirocode_intel *)); + /* + * Save the microcode patch mc in mc_save_tmp structure if it's a newer + * version. + */ + + _save_mc(mc_saved_tmp, mc, &mc_saved_count); + + /* + * Save the mc_save_tmp in global mc_saved_data. + */ + ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); + if (ret) { + pr_err("Can not save microcode patch.\n"); + goto out; + } + + show_saved_mc(); + + /* + * Free old saved microcod data. + */ + if (mc_saved) { + for (i = 0; i < mc_saved_count_init; i++) + kfree(mc_saved[i]); + kfree(mc_saved); + } + +out: + cpu_hotplug_driver_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(save_mc_for_early); +#endif + +static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; +static __init enum ucode_state +scan_microcode(unsigned long start, unsigned long end, + struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + struct ucode_cpu_info *uci) +{ + unsigned int size = end - start + 1; + struct cpio_data cd; + long offset = 0; +#ifdef CONFIG_X86_32 + char *p = (char *)__pa_symbol(ucode_name); +#else + char *p = ucode_name; +#endif + + cd.data = NULL; + cd.size = 0; + + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) + return UCODE_ERROR; + + + return get_matching_model_microcode(0, start, cd.data, cd.size, + mc_saved_data, mc_saved_in_initrd, + uci); +} + +/* + * Print ucode update info. + */ +static void __cpuinit +print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) +{ + int cpu = smp_processor_id(); + + pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", + cpu, + uci->cpu_sig.rev, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); +} + +#ifdef CONFIG_X86_32 + +static int delay_ucode_info; +static int current_mc_date; + +/* + * Print early updated ucode info after printk works. This is delayed info dump. + */ +void __cpuinit show_ucode_info_early(void) +{ + struct ucode_cpu_info uci; + + if (delay_ucode_info) { + collect_cpu_info_early(&uci); + print_ucode_info(&uci, current_mc_date); + delay_ucode_info = 0; + } +} + +/* + * At this point, we can not call printk() yet. Keep microcode patch number in + * mc_saved_data.mc_saved and delay printing microcode info in + * show_ucode_info_early() until printk() works. + */ +static void __cpuinit print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + int *delay_ucode_info_p; + int *current_mc_date_p; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info); + current_mc_date_p = (int *)__pa_symbol(¤t_mc_date); + + *delay_ucode_info_p = 1; + *current_mc_date_p = mc_intel->hdr.date; +} +#else + +/* + * Flush global tlb. We only do this in x86_64 where paging has been enabled + * already and PGE should be enabled as well. + */ +static inline void __cpuinit flush_tlb_early(void) +{ + __native_flush_tlb_global_irq_disabled(); +} + +static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + print_ucode_info(uci, mc_intel->hdr.date); +} +#endif + +static int apply_microcode_early(struct mc_saved_data *mc_saved_data, + struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + unsigned int val[2]; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return 0; + + /* write microcode via MSR 0x79 */ + native_wrmsr(MSR_IA32_UCODE_WRITE, + (unsigned long) mc_intel->bits, + (unsigned long) mc_intel->bits >> 16 >> 16); + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + if (val[1] != mc_intel->hdr.rev) + return -1; + +#ifdef CONFIG_X86_64 + /* Flush global tlb. This is precaution. */ + flush_tlb_early(); +#endif + uci->cpu_sig.rev = val[1]; + + print_ucode(uci); + + return 0; +} + +/* + * This function converts microcode patch offsets previously stored in + * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. + */ +int __init save_microcode_in_initrd(void) +{ + unsigned int count = mc_saved_data.mc_saved_count; + struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; + int ret = 0; + + if (count == 0) + return ret; + + microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count); + ret = save_microcode(&mc_saved_data, mc_saved, count); + if (ret) + pr_err("Can not save microcod patches from initrd"); + + show_saved_mc(); + + return ret; +} + +static void __init +_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + unsigned long initrd_start_early, + unsigned long initrd_end_early, + struct ucode_cpu_info *uci) +{ + collect_cpu_info_early(uci); + scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data, + mc_saved_in_initrd, uci); + load_microcode(mc_saved_data, mc_saved_in_initrd, + initrd_start_early, uci); + apply_microcode_early(mc_saved_data, uci); +} + +void __init +load_ucode_intel_bsp(void) +{ + u64 ramdisk_image, ramdisk_size; + unsigned long initrd_start_early, initrd_end_early; + struct ucode_cpu_info uci; +#ifdef CONFIG_X86_32 + struct boot_params *boot_params_p; + + boot_params_p = (struct boot_params *)__pa_symbol(&boot_params); + ramdisk_image = boot_params_p->hdr.ramdisk_image; + ramdisk_size = boot_params_p->hdr.ramdisk_size; + initrd_start_early = ramdisk_image; + initrd_end_early = initrd_start_early + ramdisk_size; + + _load_ucode_intel_bsp( + (struct mc_saved_data *)__pa_symbol(&mc_saved_data), + (unsigned long *)__pa_symbol(&mc_saved_in_initrd), + initrd_start_early, initrd_end_early, &uci); +#else + ramdisk_image = boot_params.hdr.ramdisk_image; + ramdisk_size = boot_params.hdr.ramdisk_size; + initrd_start_early = ramdisk_image + PAGE_OFFSET; + initrd_end_early = initrd_start_early + ramdisk_size; + + _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, + initrd_start_early, initrd_end_early, &uci); +#endif +} + +void __cpuinit load_ucode_intel_ap(void) +{ + struct mc_saved_data *mc_saved_data_p; + struct ucode_cpu_info uci; + unsigned long *mc_saved_in_initrd_p; + unsigned long initrd_start_addr; +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p; + + mc_saved_in_initrd_p = + (unsigned long *)__pa_symbol(mc_saved_in_initrd); + mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data); + initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start); + initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p); +#else + mc_saved_data_p = &mc_saved_data; + mc_saved_in_initrd_p = mc_saved_in_initrd; + initrd_start_addr = initrd_start; +#endif + + /* + * If there is no valid ucode previously saved in memory, no need to + * update ucode on this AP. + */ + if (mc_saved_data_p->mc_saved_count == 0) + return; + + collect_cpu_info_early(&uci); + load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, + initrd_start_addr, &uci); + apply_microcode_early(mc_saved_data_p, &uci); +} -- cgit v1.2.2 From 63b553c68db5a8d4febcd1010b194333d2b02e1c Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:29 -0800 Subject: x86/head_32.S: Early update ucode in 32-bit This updates ucode in 32-bit kernel on BSP and AP. At this point, there is no paging and no virtual address yet. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-10-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 8e7f6556028f..2f705307c8d8 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -144,6 +144,11 @@ ENTRY(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif +#ifdef CONFIG_MICROCODE_EARLY + /* Early load ucode on BSP. */ + call load_ucode_bsp +#endif + /* * Initialize page tables. This creates a PDE and a set of page * tables, which are located immediately beyond __brk_base. The variable @@ -299,6 +304,12 @@ ENTRY(startup_32_smp) movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp +#ifdef CONFIG_MICROCODE_EARLY + /* Early load ucode on AP. */ + call load_ucode_ap +#endif + + default_entry: /* * New page tables may be in 4Mbyte page mode and may -- cgit v1.2.2 From feddc9de8bf69415da6f96eca0219186b70d145a Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 20 Dec 2012 23:44:30 -0800 Subject: x86/head64.c: Early update ucode in 64-bit This updates ucode on BSP in 64-bit mode. Paging and virtual address are working now. Signed-off-by: Fenghua Yu Link: http://lkml.kernel.org/r/1356075872-3054-11-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head64.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 57334f4cd3af..3ff35705fa6e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -26,6 +26,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -170,6 +171,11 @@ void __init x86_64_start_kernel(char * real_mode_data) copy_bootdata(__va(real_mode_data)); + /* + * Load microcode early on BSP. + */ + load_ucode_bsp(); + if (console_loglevel == 10) early_printk("Kernel alive\n"); -- cgit v1.2.2 From 6bf08a8dcd1ef13e542f08fc3b1ce6cf64ae63b6 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Tue, 29 Jan 2013 16:32:16 -0500 Subject: x86, AMD: Clean up init_amd() Clean up multiple declarations of variable used for rd/wrmsr. Signed-off-by: Boris Ostrovsky Link: http://lkml.kernel.org/r/1359495136-23244-1-git-send-email-ostr@amd64.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/amd.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15239fffd6fe..dd4a5b685a00 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -518,10 +518,9 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 dummy; - -#ifdef CONFIG_SMP unsigned long long value; +#ifdef CONFIG_SMP /* * Disable TLB flush filter by setting HWCR.FFDIS on K8 * bit 6 of msr C001_0015 @@ -559,12 +558,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) * (AMD Erratum #110, docId: 25759). */ if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { - u64 val; - clear_cpu_cap(c, X86_FEATURE_LAHF_LM); - if (!rdmsrl_amd_safe(0xc001100d, &val)) { - val &= ~(1ULL << 32); - wrmsrl_amd_safe(0xc001100d, val); + if (!rdmsrl_amd_safe(0xc001100d, &value)) { + value &= ~(1ULL << 32); + wrmsrl_amd_safe(0xc001100d, value); } } @@ -617,13 +614,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) if ((c->x86 == 0x15) && (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { - u64 val; - if (!rdmsrl_safe(0xc0011005, &val)) { - val |= 1ULL << 54; - wrmsrl_safe(0xc0011005, val); - rdmsrl(0xc0011005, val); - if (val & (1ULL << 54)) { + if (!rdmsrl_safe(0xc0011005, &value)) { + value |= 1ULL << 54; + wrmsrl_safe(0xc0011005, value); + rdmsrl(0xc0011005, value); + if (value & (1ULL << 54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); printk(KERN_INFO FW_INFO "CPU: Re-enabling " "disabled Topology Extensions Support\n"); @@ -637,11 +633,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) */ 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); + if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { + value |= 0x1E; + wrmsrl_safe(0xc0011021, value); } } -- cgit v1.2.2 From f0322bd341fd63261527bf84afd3272bcc2e8dd3 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Tue, 29 Jan 2013 16:32:49 -0500 Subject: x86, AMD: Enable WC+ memory type on family 10 processors In some cases BIOS may not enable WC+ memory type on family 10 processors, instead converting what would be WC+ memory to CD type. On guests using nested pages this could result in performance degradation. This patch enables WC+. Signed-off-by: Boris Ostrovsky Link: http://lkml.kernel.org/r/1359495169-23278-1-git-send-email-ostr@amd64.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/amd.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dd4a5b685a00..721ef3208eb5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -698,13 +698,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - /* - * Disable GART TLB Walk Errors on Fam10h. We do this here - * because this is always needed when GART is enabled, even in a - * kernel which has no MCE support built in. - */ if (c->x86 == 0x10) { /* + * Disable GART TLB Walk Errors on Fam10h. We do this here + * because this is always needed when GART is enabled, even in a + * kernel which has no MCE support built in. * BIOS should disable GartTlbWlk Errors themself. If * it doesn't do it here as suggested by the BKDG. * @@ -718,6 +716,19 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) mask |= (1 << 10); wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask); } + + /* + * On family 10h BIOS may not have properly enabled WC+ support, + * causing it to be converted to CD memtype. This may result in + * performance degradation for certain nested-paging guests. + * Prevent this conversion by clearing bit 24 in + * MSR_AMD64_BU_CFG2. + */ + if (c->x86 == 0x10) { + rdmsrl(MSR_AMD64_BU_CFG2, value); + value &= ~(1ULL << 24); + wrmsrl(MSR_AMD64_BU_CFG2, value); + } } rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); -- cgit v1.2.2 From ea93a6e2e73c5a1a8d1d60098f1ca5618fd5aca1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 12 Nov 2012 14:19:03 -0500 Subject: amd64: get rid of useless RESTORE_TOP_OF_STACK in stub_execve() we are not going to return via SYSRET anyway. Signed-off-by: Al Viro --- arch/x86/kernel/entry_64.S | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 07a7a04529bc..2f2f57ac3748 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -886,7 +886,6 @@ ENTRY(stub_execve) SAVE_REST FIXUP_TOP_OF_STACK %r11 call sys_execve - RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) RESTORE_REST jmp int_ret_from_sys_call -- cgit v1.2.2 From b3af11afe06abdcf980b5f5c0b44dc46c496ddc3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 19 Nov 2012 22:00:52 -0500 Subject: x86: get rid of pt_regs argument of iopl(2) Signed-off-by: Al Viro --- arch/x86/kernel/entry_32.S | 1 - arch/x86/kernel/entry_64.S | 31 +++++++++++++------------------ arch/x86/kernel/ioport.c | 3 ++- 3 files changed, 15 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 6ed91d9980e2..415c6346d8bf 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -738,7 +738,6 @@ ENTRY(ptregs_##name) ; \ CFI_ENDPROC; \ ENDPROC(ptregs_##name) -PTREGSCALL1(iopl) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2f2f57ac3748..4486fee3999f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -828,23 +828,6 @@ int_restore_rest: CFI_ENDPROC END(system_call) -/* - * Certain special system calls that need to save a complete full stack frame. - */ - .macro PTREGSCALL label,func,arg -ENTRY(\label) - PARTIAL_FRAME 1 8 /* offset 8: return address */ - subq $REST_SKIP, %rsp - CFI_ADJUST_CFA_OFFSET REST_SKIP - call save_rest - DEFAULT_FRAME 0 8 /* offset 8: return address */ - leaq 8(%rsp), \arg /* pt_regs pointer */ - call \func - jmp ptregscall_common - CFI_ENDPROC -END(\label) - .endm - .macro FORK_LIKE func ENTRY(stub_\func) CFI_STARTPROC @@ -861,10 +844,22 @@ ENTRY(stub_\func) END(stub_\func) .endm + .macro FIXED_FRAME label,func +ENTRY(\label) + CFI_STARTPROC + PARTIAL_FRAME 0 8 /* offset 8: return address */ + FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET + call \func + RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET + ret + CFI_ENDPROC +END(\label) + .endm + FORK_LIKE clone FORK_LIKE fork FORK_LIKE vfork - PTREGSCALL stub_iopl, sys_iopl, %rsi + FIXED_FRAME stub_iopl, sys_iopl ENTRY(ptregscall_common) DEFAULT_FRAME 1 8 /* offset 8: return address */ diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 8c968974253d..4ddaf66ea35f 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -93,8 +93,9 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * on system-call entry - see also fork() and the signal handling * code. */ -long sys_iopl(unsigned int level, struct pt_regs *regs) +SYSCALL_DEFINE1(iopl, unsigned int, level) { + struct pt_regs *regs = current_pt_regs(); unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; -- cgit v1.2.2 From 3fe26fa34da029263067b48836e740c1ddffbd91 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 12 Nov 2012 14:32:42 -0500 Subject: x86: get rid of pt_regs argument in sigreturn variants Signed-off-by: Al Viro --- arch/x86/kernel/entry_32.S | 23 ----------------------- arch/x86/kernel/entry_64.S | 2 -- arch/x86/kernel/signal.c | 9 ++++++--- 3 files changed, 6 insertions(+), 28 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 415c6346d8bf..e132cf6ea140 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -702,12 +702,6 @@ END(syscall_badsys) /* * System calls that need a pt_regs pointer. */ -#define PTREGSCALL0(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - #define PTREGSCALL1(name) \ ENTRY(ptregs_##name) ; \ leal 4(%esp),%edx; \ @@ -723,23 +717,6 @@ ENTRY(ptregs_##name) ; \ jmp sys_##name; \ ENDPROC(ptregs_##name) -#define PTREGSCALL3(name) \ -ENTRY(ptregs_##name) ; \ - CFI_STARTPROC; \ - leal 4(%esp),%eax; \ - pushl_cfi %eax; \ - movl PT_EDX(%eax),%ecx; \ - movl PT_ECX(%eax),%edx; \ - movl PT_EBX(%eax),%eax; \ - call sys_##name; \ - addl $4,%esp; \ - CFI_ADJUST_CFA_OFFSET -4; \ - ret; \ - CFI_ENDPROC; \ -ENDPROC(ptregs_##name) - -PTREGSCALL0(sigreturn) -PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) PTREGSCALL1(vm86old) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 4486fee3999f..197512242e3b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -896,7 +896,6 @@ ENTRY(stub_rt_sigreturn) addq $8, %rsp PARTIAL_FRAME 0 SAVE_REST - movq %rsp,%rdi FIXUP_TOP_OF_STACK %r11 call sys_rt_sigreturn movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer @@ -911,7 +910,6 @@ ENTRY(stub_x32_rt_sigreturn) addq $8, %rsp PARTIAL_FRAME 0 SAVE_REST - movq %rsp,%rdi FIXUP_TOP_OF_STACK %r11 call sys32_x32_rt_sigreturn movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d6bf1f34a6e9..38ba7e56e161 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -597,8 +597,9 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, * Do a signal return; undo the signal stack. */ #ifdef CONFIG_X86_32 -unsigned long sys_sigreturn(struct pt_regs *regs) +unsigned long sys_sigreturn(void) { + struct pt_regs *regs = current_pt_regs(); struct sigframe __user *frame; unsigned long ax; sigset_t set; @@ -625,8 +626,9 @@ badframe: } #endif /* CONFIG_X86_32 */ -long sys_rt_sigreturn(struct pt_regs *regs) +long sys_rt_sigreturn(void) { + struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; unsigned long ax; sigset_t set; @@ -843,8 +845,9 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) } #ifdef CONFIG_X86_X32_ABI -asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) +asmlinkage long sys32_x32_rt_sigreturn(void) { + struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_x32 __user *frame; sigset_t set; unsigned long ax; -- cgit v1.2.2 From 49cb25e92902ba24bd38c350114f8695493b262f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 12 Nov 2012 14:38:28 -0500 Subject: x86: get rid of pt_regs argument in vm86/vm86old Signed-off-by: Al Viro --- arch/x86/kernel/entry_32.S | 21 --------------------- arch/x86/kernel/vm86_32.c | 8 ++++---- 2 files changed, 4 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index e132cf6ea140..352e5a9279ec 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -699,27 +699,6 @@ END(syscall_badsys) */ .popsection -/* - * System calls that need a pt_regs pointer. - */ -#define PTREGSCALL1(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%edx; \ - movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - -#define PTREGSCALL2(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%ecx; \ - movl (PT_ECX+4)(%esp),%edx; \ - movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - -PTREGSCALL2(vm86) -PTREGSCALL1(vm86old) - .macro FIXUP_ESPFIX_STACK /* * Switch back for ESPFIX stack to the normal zerobased stack diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 1dfe69cc78a8..1cf5766dde16 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -202,7 +202,7 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs) +int sys_vm86old(struct vm86_struct __user *v86) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -222,7 +222,7 @@ int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs) if (tmp) goto out; memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus); - info.regs32 = regs; + info.regs32 = current_pt_regs(); tsk->thread.vm86_info = v86; do_sys_vm86(&info, tsk); ret = 0; /* we never return here */ @@ -231,7 +231,7 @@ out: } -int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs) +int sys_vm86(unsigned long cmd, unsigned long arg) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -272,7 +272,7 @@ int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs) ret = -EFAULT; if (tmp) goto out; - info.regs32 = regs; + info.regs32 = current_pt_regs(); info.vm86plus.is_vm86pus = 1; tsk->thread.vm86_info = (struct vm86_struct __user *)v86; do_sys_vm86(&info, tsk); -- cgit v1.2.2 From 15ce1f7154c80693cec4f8a5309e8c8a06fb2541 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 16:09:20 -0500 Subject: x86,um: switch to generic old sigsuspend() Signed-off-by: Al Viro --- arch/x86/kernel/signal.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 38ba7e56e161..057712901509 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -536,17 +536,6 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, } #ifdef CONFIG_X86_32 -/* - * Atomically swap in the new signal mask, and wait for a signal. - */ -asmlinkage int -sys_sigsuspend(int history0, int history1, old_sigset_t mask) -{ - sigset_t blocked; - siginitset(&blocked, mask); - return sigsuspend(&blocked); -} - asmlinkage int sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) -- cgit v1.2.2 From 5b3eb3ade4444c3b1419ffa23598a57f6f4bf494 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 19:14:55 -0500 Subject: x86: switch to generic old sigaction Signed-off-by: Al Viro --- arch/x86/kernel/signal.c | 47 ----------------------------------------------- 1 file changed, 47 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 057712901509..d5b1f8a912ff 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -535,53 +535,6 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, return 0; } -#ifdef CONFIG_X86_32 -asmlinkage int -sys_sigaction(int sig, const struct old_sigaction __user *act, - struct old_sigaction __user *oact) -{ - struct k_sigaction new_ka, old_ka; - int ret = 0; - - if (act) { - old_sigset_t mask; - - if (!access_ok(VERIFY_READ, act, sizeof(*act))) - return -EFAULT; - - get_user_try { - get_user_ex(new_ka.sa.sa_handler, &act->sa_handler); - get_user_ex(new_ka.sa.sa_flags, &act->sa_flags); - get_user_ex(mask, &act->sa_mask); - get_user_ex(new_ka.sa.sa_restorer, &act->sa_restorer); - } get_user_catch(ret); - - if (ret) - return -EFAULT; - siginitset(&new_ka.sa.sa_mask, mask); - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact))) - return -EFAULT; - - put_user_try { - put_user_ex(old_ka.sa.sa_handler, &oact->sa_handler); - put_user_ex(old_ka.sa.sa_flags, &oact->sa_flags); - put_user_ex(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); - put_user_ex(old_ka.sa.sa_restorer, &oact->sa_restorer); - } put_user_catch(ret); - - if (ret) - return -EFAULT; - } - - return ret; -} -#endif /* CONFIG_X86_32 */ - /* * Do a signal return; undo the signal stack. */ -- cgit v1.2.2 From f76e39c531304b114e27c3dd3e0036f56cd33df1 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 4 Feb 2013 10:13:15 +0100 Subject: x86/intel/cacheinfo: Shut up annoying warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I've been getting the following warning when doing randbuilds since forever. Now it finally pissed me off just the perfect amount so that I can fix it. arch/x86/kernel/cpu/intel_cacheinfo.c:489:27: warning: ‘cache_disable_0’ defined but not used [-Wunused-variable] arch/x86/kernel/cpu/intel_cacheinfo.c:491:27: warning: ‘cache_disable_1’ defined but not used [-Wunused-variable] arch/x86/kernel/cpu/intel_cacheinfo.c:524:27: warning: ‘subcaches’ defined but not used [-Wunused-variable] It happens because in randconfigs where CONFIG_SYSFS is not set, the whole sysfs-interface to L3 cache index disabling is remaining unused and gcc correctly warns about it. Make it optional, depending on CONFIG_SYSFS too, as is the case with other sysfs-related machinery in this file. Signed-off-by: Borislav Petkov Cc: Andreas Herrmann Link: http://lkml.kernel.org/r/1359969195-27362-1-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_cacheinfo.c | 7 +++---- 1 file changed, 3 insertions(+), 4 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 fe9edec6698a..84c1309c4c0c 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -298,8 +298,7 @@ struct _cache_attr { unsigned int); }; -#ifdef CONFIG_AMD_NB - +#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS) /* * L3 cache descriptors */ @@ -524,9 +523,9 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, static struct _cache_attr subcaches = __ATTR(subcaches, 0644, show_subcaches, store_subcaches); -#else /* CONFIG_AMD_NB */ +#else #define amd_init_l3_cache(x, y) -#endif /* CONFIG_AMD_NB */ +#endif /* CONFIG_AMD_NB && CONFIG_SYSFS */ static int __cpuinit cpuid4_cache_lookup_regs(int index, -- cgit v1.2.2 From 2c53c3dd0b6497484b29fd49d34ef98acbc14577 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Feb 2013 11:26:24 -0600 Subject: perf/x86/amd: Rework northbridge event constraints handler Code simplification. No functional changes. Signed-off-by: Robert Richter Signed-off-by: Jacob Shin Acked-by: Stephane Eranian Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Robert Richter Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-2-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_amd.c | 68 ++++++++++++++---------------------- 1 file changed, 26 insertions(+), 42 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index c93bc4e813a0..e7963c7af683 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -256,9 +256,8 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; - struct perf_event *old = NULL; - int max = x86_pmu.num_counters; - int i, j, k = -1; + struct perf_event *old; + int idx, new = -1; /* * if not NB event or no NB, then no constraints @@ -276,48 +275,33 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) * because of successive calls to x86_schedule_events() from * hw_perf_group_sched_in() without hw_perf_enable() */ - for (i = 0; i < max; i++) { - /* - * keep track of first free slot - */ - if (k == -1 && !nb->owners[i]) - k = i; + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (new == -1 || hwc->idx == idx) + /* assign free slot, prefer hwc->idx */ + old = cmpxchg(nb->owners + idx, NULL, event); + else if (nb->owners[idx] == event) + /* event already present */ + old = event; + else + continue; + + if (old && old != event) + continue; + + /* reassign to this slot */ + if (new != -1) + cmpxchg(nb->owners + new, event, NULL); + new = idx; /* already present, reuse */ - if (nb->owners[i] == event) - goto done; - } - /* - * not present, so grab a new slot - * starting either at: - */ - if (hwc->idx != -1) { - /* previous assignment */ - i = hwc->idx; - } else if (k != -1) { - /* start from free slot found */ - i = k; - } else { - /* - * event not found, no slot found in - * first pass, try again from the - * beginning - */ - i = 0; - } - j = i; - do { - old = cmpxchg(nb->owners+i, NULL, event); - if (!old) + if (old == event) break; - if (++i == max) - i = 0; - } while (i != j); -done: - if (!old) - return &nb->event_constraints[i]; - - return &emptyconstraint; + } + + if (new == -1) + return &emptyconstraint; + + return &nb->event_constraints[new]; } static struct amd_nb *amd_alloc_nb(int cpu) -- cgit v1.2.2 From 4dd4c2ae555d8a91e8c5bf1cd56807a35764436a Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Feb 2013 11:26:25 -0600 Subject: perf/x86/amd: Generalize northbridge constraints code for family 15h Generalize northbridge constraints code for family 10h so that later we can reuse the same code path with other AMD processor families that have the same northbridge event constraints. Signed-off-by: Robert Richter Signed-off-by: Jacob Shin Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-3-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_amd.c | 43 +++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 18 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index e7963c7af683..f8c9dfbd6613 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -188,19 +188,12 @@ static inline int amd_has_nb(struct cpu_hw_events *cpuc) return nb && nb->nb_id != -1; } -static void amd_put_event_constraints(struct cpu_hw_events *cpuc, - struct perf_event *event) +static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; int i; - /* - * only care about NB events - */ - if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc))) - return; - /* * need to scan whole list because event may not have * been assigned during scheduling @@ -247,24 +240,19 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, * * Given that resources are allocated (cmpxchg), they must be * eventually freed for others to use. This is accomplished by - * calling amd_put_event_constraints(). + * calling __amd_put_nb_event_constraints() * * Non NB events are not impacted by this restriction. */ static struct event_constraint * -amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, + struct event_constraint *c) { struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; struct perf_event *old; int idx, new = -1; - /* - * if not NB event or no NB, then no constraints - */ - if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc))) - return &unconstrained; - /* * detect if already present, if so reuse * @@ -275,7 +263,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) * because of successive calls to x86_schedule_events() from * hw_perf_group_sched_in() without hw_perf_enable() */ - for (idx = 0; idx < x86_pmu.num_counters; idx++) { + for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) { if (new == -1 || hwc->idx == idx) /* assign free slot, prefer hwc->idx */ old = cmpxchg(nb->owners + idx, NULL, event); @@ -391,6 +379,25 @@ static void amd_pmu_cpu_dead(int cpu) } } +static struct event_constraint * +amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + /* + * if not NB event or no NB, then no constraints + */ + if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))) + return &unconstrained; + + return __amd_get_nb_event_constraints(cpuc, event, &unconstrained); +} + +static void amd_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)) + __amd_put_nb_event_constraints(cpuc, event); +} + PMU_FORMAT_ATTR(event, "config:0-7,32-35"); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); -- cgit v1.2.2 From 9f19010af8c651879ac2c36f1a808a3a4419cd40 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Wed, 6 Feb 2013 11:26:26 -0600 Subject: perf/x86/amd: Use proper naming scheme for AMD bit field definitions Update these AMD bit field names to be consistent with naming convention followed by the rest of the file. Signed-off-by: Jacob Shin Acked-by: Stephane Eranian Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-4-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_amd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index f8c9dfbd6613..aea8c2021f78 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -156,9 +156,9 @@ static int amd_pmu_hw_config(struct perf_event *event) event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | ARCH_PERFMON_EVENTSEL_OS); else if (event->attr.exclude_host) - event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY; + event->hw.config |= AMD64_EVENTSEL_GUESTONLY; else if (event->attr.exclude_guest) - event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY; + event->hw.config |= AMD64_EVENTSEL_HOSTONLY; if (event->attr.type != PERF_TYPE_RAW) return 0; @@ -336,7 +336,7 @@ static void amd_pmu_cpu_starting(int cpu) struct amd_nb *nb; int i, nb_id; - cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; if (boot_cpu_data.x86_max_cores < 2) return; @@ -669,7 +669,7 @@ void amd_pmu_disable_virt(void) * SVM is disabled the Guest-only bits still gets set and the counter * will not count anything. */ - cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; /* Reload all events */ x86_pmu_disable_all(); -- cgit v1.2.2 From 4c1fd17a1cb32bc4f429c7a5ff9a91a3bffdb8fa Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Wed, 6 Feb 2013 11:26:27 -0600 Subject: perf/x86: Move MSR address offset calculation to architecture specific files Move counter index to MSR address offset calculation to architecture specific files. This prepares the way for perf_event_amd to enable counter addresses that are not contiguous -- for example AMD Family 15h processors have 6 core performance counters starting at 0xc0010200 and 4 northbridge performance counters starting at 0xc0010240. Signed-off-by: Jacob Shin Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-5-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.h | 21 +++++------------- arch/x86/kernel/cpu/perf_event_amd.c | 42 ++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 16 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 115c1ea97746..a7f06a90d2e7 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -325,6 +325,7 @@ struct x86_pmu { int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; unsigned perfctr; + int (*addr_offset)(int index, bool eventsel); u64 (*event_map)(int); int max_events; int num_counters; @@ -446,28 +447,16 @@ extern u64 __read_mostly hw_cache_extra_regs u64 x86_perf_event_update(struct perf_event *event); -static inline int x86_pmu_addr_offset(int index) -{ - int offset; - - /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ - alternative_io(ASM_NOP2, - "shll $1, %%eax", - X86_FEATURE_PERFCTR_CORE, - "=a" (offset), - "a" (index)); - - return offset; -} - static inline unsigned int x86_pmu_config_addr(int index) { - return x86_pmu.eventsel + x86_pmu_addr_offset(index); + return x86_pmu.eventsel + (x86_pmu.addr_offset ? + x86_pmu.addr_offset(index, true) : index); } static inline unsigned int x86_pmu_event_addr(int index) { - return x86_pmu.perfctr + x86_pmu_addr_offset(index); + return x86_pmu.perfctr + (x86_pmu.addr_offset ? + x86_pmu.addr_offset(index, false) : index); } int x86_setup_perfctr(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index aea8c2021f78..b60f31caeda0 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -132,6 +132,47 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } +/* + * Previously calculated offsets + */ +static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly; +static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; + +/* + * Legacy CPUs: + * 4 counters starting at 0xc0010000 each offset by 1 + * + * CPUs with core performance counter extensions: + * 6 counters starting at 0xc0010200 each offset by 2 + */ +static inline int amd_pmu_addr_offset(int index, bool eventsel) +{ + int offset; + + if (!index) + return index; + + if (eventsel) + offset = event_offsets[index]; + else + offset = count_offsets[index]; + + if (offset) + return offset; + + if (!cpu_has_perfctr_core) + offset = index; + else + offset = index << 1; + + if (eventsel) + event_offsets[index] = offset; + else + count_offsets[index] = offset; + + return offset; +} + static int amd_pmu_hw_config(struct perf_event *event) { int ret; @@ -578,6 +619,7 @@ static __initconst const struct x86_pmu amd_pmu = { .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, + .addr_offset = amd_pmu_addr_offset, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, -- cgit v1.2.2 From 0fbdad078a70ed72248c3d30fe32e45e83be00d1 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Wed, 6 Feb 2013 11:26:28 -0600 Subject: perf/x86: Allow for architecture specific RDPMC indexes Similar to config_base and event_base, allow architecture specific RDPMC ECX values. Signed-off-by: Jacob Shin Acked-by: Stephane Eranian Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-6-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.h | 6 ++++++ arch/x86/kernel/cpu/perf_event_amd.c | 6 ++++++ 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c0df5ed2e048..bf0f01aea994 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -829,7 +829,7 @@ static inline void x86_assign_hw_event(struct perf_event *event, } else { hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); - hwc->event_base_rdpmc = hwc->idx; + hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx); } } diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index a7f06a90d2e7..7f5c75c2afdd 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -326,6 +326,7 @@ struct x86_pmu { unsigned eventsel; unsigned perfctr; int (*addr_offset)(int index, bool eventsel); + int (*rdpmc_index)(int index); u64 (*event_map)(int); int max_events; int num_counters; @@ -459,6 +460,11 @@ static inline unsigned int x86_pmu_event_addr(int index) x86_pmu.addr_offset(index, false) : index); } +static inline int x86_pmu_rdpmc_index(int index) +{ + return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index; +} + int x86_setup_perfctr(struct perf_event *event); int x86_pmu_hw_config(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index b60f31caeda0..05462f0432d5 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -173,6 +173,11 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } +static inline int amd_pmu_rdpmc_index(int index) +{ + return index; +} + static int amd_pmu_hw_config(struct perf_event *event) { int ret; @@ -620,6 +625,7 @@ static __initconst const struct x86_pmu amd_pmu = { .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .addr_offset = amd_pmu_addr_offset, + .rdpmc_index = amd_pmu_rdpmc_index, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, -- cgit v1.2.2 From 96477b4cd705c5416346aef262b0a1116cfcdd80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 12 Dec 2012 13:34:03 +0200 Subject: x86-32: Add support for 64bit get_user() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement __get_user_8() for x86-32. It will return the 64-bit result in edx:eax register pair, and ecx is used to pass in the address and return the error value. For consistency, change the register assignment for all other __get_user_x() variants, so that address is passed in ecx/rcx, the error value is returned in ecx/rcx, and eax/rax contains the actual value. [ hpa: I modified the patch so that it does NOT change the calling conventions for the existing callsites, this also means that the code is completely unchanged for 64 bits. Instead, continue to use eax for address input/error output and use the ecx:edx register pair for the output. ] This is a partial refresh of a patch [1] by Jamie Lokier from 2004. Only the minimal changes to implement 64bit get_user() were picked from the original patch. [1] http://article.gmane.org/gmane.linux.kernel/198823 Originally-by: Jamie Lokier Signed-off-by: Ville Syrjälä Link: http://lkml.kernel.org/r/1355312043-11467-1-git-send-email-ville.syrjala@linux.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/i386_ksyms_32.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 9c3bd4a2050e..0fa69127209a 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -26,6 +26,7 @@ EXPORT_SYMBOL(csum_partial_copy_generic); EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); +EXPORT_SYMBOL(__get_user_8); EXPORT_SYMBOL(__put_user_1); EXPORT_SYMBOL(__put_user_2); -- cgit v1.2.2 From cf31ec3f7fece93f3fce3ee5964e27857141ea47 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 30 Dec 2012 15:21:22 +0100 Subject: uprobes/x86: Change __skip_sstep() to actually skip the whole insn __skip_sstep() doesn't update regs->ip. Currently this is correct but only "by accident" and it doesn't skip the whole insn. Change it to advance ->ip by the length of the detected 0x66*0x90 sequence. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju --- arch/x86/kernel/uprobes.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index c71025b67462..4e33a35d659e 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -680,8 +680,11 @@ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (auprobe->insn[i] == 0x66) continue; - if (auprobe->insn[i] == 0x90) + if (auprobe->insn[i] == 0x90) { + regs->ip = uprobe_get_swbp_addr(regs); + regs->ip += i + 1; return true; + } break; } -- cgit v1.2.2 From 74e59dfc6b19e3472a7c16ad57bc831e6e647895 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 30 Dec 2012 15:54:08 +0100 Subject: uprobes: Change handle_swbp() to expose bp_vaddr to handler_chain() Change handle_swbp() to set regs->ip = bp_vaddr in advance, this is what consumer->handler() needs but uprobe_get_swbp_addr() is not exported. This also simplifies the code and makes it more consistent across the supported architectures. handle_swbp() becomes the only caller of uprobe_get_swbp_addr(). Signed-off-by: Oleg Nesterov Acked-by: Ananth N Mavinakayanahalli --- arch/x86/kernel/uprobes.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 4e33a35d659e..0ba4cfb4f412 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -681,7 +681,6 @@ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) continue; if (auprobe->insn[i] == 0x90) { - regs->ip = uprobe_get_swbp_addr(regs); regs->ip += i + 1; return true; } -- cgit v1.2.2 From 6a377ddc4e4ede2eeb9cd46ada23bbe417704fc9 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sat, 9 Feb 2013 23:08:07 -0500 Subject: xen idle: make xen-specific macro xen-specific This macro is only invoked by Xen, so make its definition specific to Xen. > set_pm_idle_to_default() < xen_set_default_idle() Signed-off-by: Len Brown Cc: xen-devel@lists.xensource.com --- arch/x86/kernel/process.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2ed787f15bf0..7ed9f6b08ba0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -396,7 +396,8 @@ void default_idle(void) EXPORT_SYMBOL(default_idle); #endif -bool set_pm_idle_to_default(void) +#ifdef CONFIG_XEN +bool xen_set_default_idle(void) { bool ret = !!pm_idle; @@ -404,6 +405,7 @@ bool set_pm_idle_to_default(void) return ret; } +#endif void stop_this_cpu(void *dummy) { local_irq_disable(); -- cgit v1.2.2 From 69fb3676df3329a7142803bb3502fa59dc0db2e3 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sun, 10 Feb 2013 01:38:39 -0500 Subject: x86 idle: remove mwait_idle() and "idle=mwait" cmdline param mwait_idle() is a C1-only idle loop intended to be more efficient than HLT, starting on Pentium-4 HT-enabled processors. But mwait_idle() has been replaced by the more general mwait_idle_with_hints(), which handles both C1 and deeper C-states. ACPI processor_idle and intel_idle use only mwait_idle_with_hints(), and no longer use mwait_idle(). Here we simplify the x86 native idle code by removing mwait_idle(), and the "idle=mwait" bootparam used to invoke it. Since Linux 3.0 there has been a boot-time warning when "idle=mwait" was invoked saying it would be removed in 2012. This removal was also noted in the (now removed:-) feature-removal-schedule.txt. After this change, kernels configured with (CONFIG_ACPI=n && CONFIG_INTEL_IDLE=n) when run on hardware that supports MWAIT will simply use HLT. If MWAIT is desired on those systems, cpuidle and the cpuidle drivers above can be enabled. Signed-off-by: Len Brown Cc: x86@kernel.org --- arch/x86/kernel/process.c | 79 +---------------------------------------------- arch/x86/kernel/smpboot.c | 2 +- 2 files changed, 2 insertions(+), 79 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 7ed9f6b08ba0..cd5a4c9ef835 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -421,27 +421,6 @@ void stop_this_cpu(void *dummy) } } -/* Default MONITOR/MWAIT with no hints, used for default C1 state */ -static void mwait_idle(void) -{ - if (!need_resched()) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle_rcuidle(1, smp_processor_id()); - if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) - clflush((void *)¤t_thread_info()->flags); - - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __sti_mwait(0, 0); - else - local_irq_enable(); - trace_power_end_rcuidle(smp_processor_id()); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); - } else - local_irq_enable(); -} - /* * On SMP it's slightly faster (but much more power-consuming!) * to poll the ->work.need_resched flag instead of waiting for the @@ -458,53 +437,6 @@ static void poll_idle(void) trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } -/* - * mwait selection logic: - * - * It depends on the CPU. For AMD CPUs that support MWAIT this is - * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings - * then depend on a clock divisor and current Pstate of the core. If - * all cores of a processor are in halt state (C1) the processor can - * enter the C1E (C1 enhanced) state. If mwait is used this will never - * happen. - * - * idle=mwait overrides this decision and forces the usage of mwait. - */ - -#define MWAIT_INFO 0x05 -#define MWAIT_ECX_EXTENDED_INFO 0x01 -#define MWAIT_EDX_C1 0xf0 - -int mwait_usable(const struct cpuinfo_x86 *c) -{ - u32 eax, ebx, ecx, edx; - - /* Use mwait if idle=mwait boot option is given */ - if (boot_option_idle_override == IDLE_FORCE_MWAIT) - return 1; - - /* - * Any idle= boot option other than idle=mwait means that we must not - * use mwait. Eg: idle=halt or idle=poll or idle=nomwait - */ - if (boot_option_idle_override != IDLE_NO_OVERRIDE) - return 0; - - if (c->cpuid_level < MWAIT_INFO) - return 0; - - cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx); - /* Check, whether EDX has extended info about MWAIT */ - if (!(ecx & MWAIT_ECX_EXTENDED_INFO)) - return 1; - - /* - * edx enumeratios MONITOR/MWAIT extensions. Check, whether - * C1 supports MWAIT - */ - return (edx & MWAIT_EDX_C1); -} - bool amd_e400_c1e_detected; EXPORT_SYMBOL(amd_e400_c1e_detected); @@ -576,13 +508,7 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) if (pm_idle) return; - if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { - /* - * One CPU supports mwait => All CPUs supports mwait - */ - pr_info("using mwait in idle threads\n"); - pm_idle = mwait_idle; - } else if (cpu_has_amd_erratum(amd_erratum_400)) { + if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); pm_idle = amd_e400_idle; @@ -606,9 +532,6 @@ static int __init idle_setup(char *str) pr_info("using polling idle threads\n"); pm_idle = poll_idle; boot_option_idle_override = IDLE_POLL; - } else if (!strcmp(str, "mwait")) { - boot_option_idle_override = IDLE_FORCE_MWAIT; - WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n"); } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ed0fe385289d..a6ceaedc396a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1369,7 +1369,7 @@ static inline void mwait_play_dead(void) void *mwait_ptr; struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info); - if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))) + if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLSH)) return; -- cgit v1.2.2 From 27be457000211a6903968dfce06d5f73f051a217 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sun, 10 Feb 2013 02:28:46 -0500 Subject: x86 idle: remove 32-bit-only "no-hlt" parameter, hlt_works_ok flag Remove 32-bit x86 a cmdline param "no-hlt", and the cpuinfo_x86.hlt_works_ok that it sets. If a user wants to avoid HLT, then "idle=poll" is much more useful, as it avoids invocation of HLT in idle, while "no-hlt" failed to do so. Indeed, hlt_works_ok was consulted in only 3 places. First, in /proc/cpuinfo where "hlt_bug yes" would be printed if and only if the user booted the system with "no-hlt" -- as there was no other code to set that flag. Second, check_hlt() would not invoke halt() if "no-hlt" were on the cmdline. Third, it was consulted in stop_this_cpu(), which is invoked by native_machine_halt()/reboot_interrupt()/smp_stop_nmi_callback() -- all cases where the machine is being shutdown/reset. The flag was not consulted in the more frequently invoked play_dead()/hlt_play_dead() used in processor offline and suspend. Since Linux-3.0 there has been a run-time notice upon "no-hlt" invocations indicating that it would be removed in 2012. Signed-off-by: Len Brown Cc: x86@kernel.org --- arch/x86/kernel/cpu/bugs.c | 27 --------------------------- arch/x86/kernel/cpu/proc.c | 2 -- arch/x86/kernel/process.c | 6 ++---- 3 files changed, 2 insertions(+), 33 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 92dfec986a48..af6455e3fcc9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -17,15 +17,6 @@ #include #include -static int __init no_halt(char *s) -{ - WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n"); - boot_cpu_data.hlt_works_ok = 0; - return 1; -} - -__setup("no-hlt", no_halt); - static int __init no_387(char *s) { boot_cpu_data.hard_math = 0; @@ -89,23 +80,6 @@ static void __init check_fpu(void) pr_warn("Hmm, FPU with FDIV bug\n"); } -static void __init check_hlt(void) -{ - if (boot_cpu_data.x86 >= 5 || paravirt_enabled()) - return; - - pr_info("Checking 'hlt' instruction... "); - if (!boot_cpu_data.hlt_works_ok) { - pr_cont("disabled\n"); - return; - } - halt(); - halt(); - halt(); - halt(); - pr_cont("OK\n"); -} - /* * Check whether we are able to run this kernel safely on SMP. * @@ -129,7 +103,6 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); #endif check_config(); - check_hlt(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 3286a92e662a..e280253f6f94 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -28,7 +28,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { seq_printf(m, "fdiv_bug\t: %s\n" - "hlt_bug\t\t: %s\n" "f00f_bug\t: %s\n" "coma_bug\t: %s\n" "fpu\t\t: %s\n" @@ -36,7 +35,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "cpuid level\t: %d\n" "wp\t\t: %s\n", c->fdiv_bug ? "yes" : "no", - c->hlt_works_ok ? "no" : "yes", c->f00f_bug ? "yes" : "no", c->coma_bug ? "yes" : "no", c->hard_math ? "yes" : "no", diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index cd5a4c9ef835..aef852eac292 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -415,10 +415,8 @@ void stop_this_cpu(void *dummy) set_cpu_online(smp_processor_id(), false); disable_local_APIC(); - for (;;) { - if (hlt_works(smp_processor_id())) - halt(); - } + for (;;) + halt(); } /* -- cgit v1.2.2 From 136867f517cbc3f8a91f035677911a6b503c3323 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Tue, 5 Feb 2013 19:57:22 -0700 Subject: x86/kvm: Fix compile warning in kvm_register_steal_time() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following compile warning in kvm_register_steal_time(): CC arch/x86/kernel/kvm.o arch/x86/kernel/kvm.c: In function ‘kvm_register_steal_time’: arch/x86/kernel/kvm.c:302:3: warning: format ‘%lx’ expects argument of type ‘long unsigned int’, but argument 3 has type ‘phys_addr_t’ [-Wformat] Introduced via: 5dfd486c4750 x86, kvm: Fix kvm's use of __pa() on percpu areas d76565344512 x86, mm: Create slow_virt_to_phys() f3c4fbb68e93 x86, mm: Use new pagetable helpers in try_preserve_large_page() 4cbeb51b860c x86, mm: Pagetable level size/shift/mask helpers a25b9316841c x86, mm: Make DEBUG_VIRTUAL work earlier in boot Signed-off-by: Shuah Khan Acked-by: Gleb Natapov Cc: Marcelo Tosatti Cc: Dave Hansen Cc: Rik van Riel Cc: shuahkhan@gmail.com Cc: avi@redhat.com Cc: gleb@redhat.com Cc: mst@redhat.com Link: http://lkml.kernel.org/r/1360119442.8356.8.camel@lorien2 Signed-off-by: Ingo Molnar --- arch/x86/kernel/kvm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa7e58b82b39..9cec20253093 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -298,8 +298,8 @@ static void kvm_register_steal_time(void) memset(st, 0, sizeof(*st)); wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED)); - printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n", - cpu, slow_virt_to_phys(st)); + pr_info("kvm-stealtime: cpu %d, msr %llx\n", + cpu, (unsigned long long) slow_virt_to_phys(st)); } static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; -- cgit v1.2.2 From cb214ede7657db458fd0b2a25ea0b28dbf900ebc Mon Sep 17 00:00:00 2001 From: Stoney Wang Date: Thu, 7 Feb 2013 10:53:02 -0800 Subject: x86/apic: Work around boot failure on HP ProLiant DL980 G7 Server systems When a HP ProLiant DL980 G7 Server boots a regular kernel, there will be intermittent lost interrupts which could result in a hang or (in extreme cases) data loss. The reason is that this system only supports x2apic physical mode, while the kernel boots with a logical-cluster default setting. This bug can be worked around by specifying the "x2apic_phys" or "nox2apic" boot option, but we want to handle this system without requiring manual workarounds. The BIOS sets ACPI_FADT_APIC_PHYSICAL in FADT table. As all apicids are smaller than 255, BIOS need to pass the control to the OS with xapic mode, according to x2apic-spec, chapter 2.9. Current code handle x2apic when BIOS pass with xapic mode enabled: When user specifies x2apic_phys, or FADT indicates PHYSICAL: 1. During madt oem check, apic driver is set with xapic logical or xapic phys driver at first. 2. enable_IR_x2apic() will enable x2apic_mode. 3. if user specifies x2apic_phys on the boot line, x2apic_phys_probe() will install the correct x2apic phys driver and use x2apic phys mode. Otherwise it will skip the driver will let x2apic_cluster_probe to take over to install x2apic cluster driver (wrong one) even though FADT indicates PHYSICAL, because x2apic_phys_probe does not check FADT PHYSICAL. Add checking x2apic_fadt_phys in x2apic_phys_probe() to fix the problem. Signed-off-by: Stoney Wang [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/x2apic_phys.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index e03a1e180e81..562a76d433c8 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -20,18 +20,19 @@ static int set_x2apic_phys_mode(char *arg) } early_param("x2apic_phys", set_x2apic_phys_mode); -static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static bool x2apic_fadt_phys(void) { - if (x2apic_phys) - return x2apic_enabled(); - else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && - (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) && - x2apic_enabled()) { + if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && + (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { printk(KERN_DEBUG "System requires x2apic physical mode\n"); - return 1; + return true; } - else - return 0; + return false; +} + +static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } static void @@ -82,7 +83,7 @@ static void init_x2apic_ldr(void) static int x2apic_phys_probe(void) { - if (x2apic_mode && x2apic_phys) + if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys())) return 1; return apic == &apic_x2apic_phys; -- cgit v1.2.2 From b15cc4a12bed8026bc70f469f514862b027b0c75 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 11 Feb 2013 13:45:12 -0600 Subject: x86, uv, uv3: Update x2apic Support for SGI UV3 This patch adds support for the SGI UV3 hub to the common x2apic functions. The primary changes are to account for the similarities between UV2 and UV3 which are encompassed within the "UVX" nomenclature. One significant difference within UV3 is the handling of the MMIOH regions which are redirected to the target blade (with the device) in a different manner. It also now has two MMIOH regions for both small and large BARs. This aids in limiting the amount of physical address space removed from real memory that's used for I/O in the max config of 64TB. Signed-off-by: Mike Travis Link: http://lkml.kernel.org/r/20130211194508.752924185@gulag1.americas.sgi.com Acked-by: Russ Anderson Reviewed-by: Dimitri Sivanich Cc: Alexander Gordeev Cc: Suresh Siddha Cc: Michael S. Tsirkin Cc: Steffen Persvold Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/x2apic_uv_x.c | 206 ++++++++++++++++++++++++++++++------- 1 file changed, 171 insertions(+), 35 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 8cfade9510a4..794f6eb54cd3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -5,7 +5,7 @@ * * SGI UV APIC functions (note: not an Intel compatible APIC) * - * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. */ #include #include @@ -91,10 +91,16 @@ static int __init early_get_pnodeid(void) m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR); uv_min_hub_revision_id = node_id.s.revision; - if (node_id.s.part_number == UV2_HUB_PART_NUMBER) - uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; - if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X) + switch (node_id.s.part_number) { + case UV2_HUB_PART_NUMBER: + case UV2_HUB_PART_NUMBER_X: uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; + break; + case UV3_HUB_PART_NUMBER: + case UV3_HUB_PART_NUMBER_X: + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + break; + } uv_hub_info->hub_revision = uv_min_hub_revision_id; pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); @@ -130,13 +136,16 @@ static void __init uv_set_apicid_hibit(void) static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int pnodeid, is_uv1, is_uv2; + int pnodeid, is_uv1, is_uv2, is_uv3; is_uv1 = !strcmp(oem_id, "SGI"); is_uv2 = !strcmp(oem_id, "SGI2"); - if (is_uv1 || is_uv2) { + is_uv3 = !strncmp(oem_id, "SGI3", 4); /* there are varieties of UV3 */ + if (is_uv1 || is_uv2 || is_uv3) { uv_hub_info->hub_revision = - is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE; + (is_uv1 ? UV1_HUB_REVISION_BASE : + (is_uv2 ? UV2_HUB_REVISION_BASE : + UV3_HUB_REVISION_BASE)); pnodeid = early_get_pnodeid(); early_get_apic_pnode_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; @@ -450,14 +459,17 @@ static __init void map_high(char *id, unsigned long base, int pshift, paddr = base << pshift; bytes = (1UL << bshift) * (max_pnode + 1); - printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, - paddr + bytes); + if (!paddr) { + pr_info("UV: Map %s_HI base address NULL\n", id); + return; + } + pr_info("UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) init_extra_mapping_uc(paddr, bytes); else init_extra_mapping_wb(paddr, bytes); - } + static __init void map_gru_high(int max_pnode) { union uvh_rh_gam_gru_overlay_config_mmr_u gru; @@ -468,7 +480,8 @@ static __init void map_gru_high(int max_pnode) map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)gru.s.base << shift); gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); - + } else { + pr_info("UV: GRU disabled\n"); } } @@ -480,23 +493,146 @@ static __init void map_mmr_high(int max_pnode) mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); if (mmr.s.enable) map_high("MMR", mmr.s.base, shift, shift, max_pnode, map_uc); + else + pr_info("UV: MMR disabled\n"); +} + +/* + * This commonality works because both 0 & 1 versions of the MMIOH OVERLAY + * and REDIRECT MMR regs are exactly the same on UV3. + */ +struct mmioh_config { + unsigned long overlay; + unsigned long redirect; + char *id; +}; + +static __initdata struct mmioh_config mmiohs[] = { + { + UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR, + UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR, + "MMIOH0" + }, + { + UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR, + UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR, + "MMIOH1" + }, +}; + +static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) +{ + union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay; + unsigned long mmr; + unsigned long base; + int i, n, shift, m_io, max_io; + int nasid, lnasid, fi, li; + char *id; + + id = mmiohs[index].id; + overlay.v = uv_read_local_mmr(mmiohs[index].overlay); + pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", + id, overlay.v, overlay.s3.base, overlay.s3.m_io); + if (!overlay.s3.enable) { + pr_info("UV: %s disabled\n", id); + return; + } + + shift = UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT; + base = (unsigned long)overlay.s3.base; + m_io = overlay.s3.m_io; + mmr = mmiohs[index].redirect; + n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH; + min_pnode *= 2; /* convert to NASID */ + max_pnode *= 2; + max_io = lnasid = fi = li = -1; + + for (i = 0; i < n; i++) { + union uv3h_rh_gam_mmioh_redirect_config0_mmr_u redirect; + + redirect.v = uv_read_local_mmr(mmr + i * 8); + nasid = redirect.s3.nasid; + if (nasid < min_pnode || max_pnode < nasid) + nasid = -1; /* invalid NASID */ + + if (nasid == lnasid) { + li = i; + if (i != n-1) /* last entry check */ + continue; + } + + /* check if we have a cached (or last) redirect to print */ + if (lnasid != -1 || (i == n-1 && nasid != -1)) { + unsigned long addr1, addr2; + int f, l; + + if (lnasid == -1) { + f = l = i; + lnasid = nasid; + } else { + f = fi; + l = li; + } + addr1 = (base << shift) + + f * (unsigned long)(1 << m_io); + addr2 = (base << shift) + + (l + 1) * (unsigned long)(1 << m_io); + pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", + id, fi, li, lnasid, addr1, addr2); + if (max_io < l) + max_io = l; + } + fi = li = i; + lnasid = nasid; + } + + pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", + id, base, shift, m_io, max_io); + + if (max_io >= 0) + map_high(id, base, shift, m_io, max_io, map_uc); } -static __init void map_mmioh_high(int max_pnode) +static __init void map_mmioh_high(int min_pnode, int max_pnode) { union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; - int shift; + unsigned long mmr, base; + int shift, enable, m_io, n_io; - mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - if (is_uv1_hub() && mmioh.s1.enable) { - shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io, - max_pnode, map_uc); + if (is_uv3_hub()) { + /* Map both MMIOH Regions */ + map_mmioh_high_uv3(0, min_pnode, max_pnode); + map_mmioh_high_uv3(1, min_pnode, max_pnode); + return; } - if (is_uv2_hub() && mmioh.s2.enable) { + + if (is_uv1_hub()) { + mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s1.enable; + base = mmioh.s1.base; + m_io = mmioh.s1.m_io; + n_io = mmioh.s1.n_io; + } else if (is_uv2_hub()) { + mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io, - max_pnode, map_uc); + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s2.enable; + base = mmioh.s2.base; + m_io = mmioh.s2.m_io; + n_io = mmioh.s2.n_io; + } else + return; + + if (enable) { + max_pnode &= (1 << n_io) - 1; + pr_info( + "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", + base, shift, m_io, n_io, max_pnode); + map_high("MMIOH", base, shift, m_io, max_pnode, map_uc); + } else { + pr_info("UV: MMIOH disabled\n"); } } @@ -724,42 +860,41 @@ void uv_nmi_init(void) void __init uv_system_init(void) { union uvh_rh_gam_config_mmr_u m_n_config; - union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; union uvh_node_id_u node_id; unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; - int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io; - int gnode_extra, max_pnode = 0; + int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; + int gnode_extra, min_pnode = 999999, max_pnode = -1; unsigned long mmr_base, present, paddr; - unsigned short pnode_mask, pnode_io_mask; + unsigned short pnode_mask; + char *hub = (is_uv1_hub() ? "UV1" : + (is_uv2_hub() ? "UV2" : + "UV3")); - printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2"); + pr_info("UV: Found %s hub\n", hub); map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; - mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io; + pnode_mask = (1 << n_val) - 1; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; - pnode_mask = (1 << n_val) - 1; - pnode_io_mask = (1 << n_io) - 1; node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n", - n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask); + pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x\n", + n_val, m_val, pnode_mask, gnode_upper, gnode_extra); - printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base); + pr_info("UV: global MMR base 0x%lx\n", mmr_base); for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) uv_possible_blades += hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); /* uv_num_possible_blades() is really the hub count */ - printk(KERN_INFO "UV: Found %d blades, %d hubs\n", + pr_info("UV: Found %d blades, %d hubs\n", is_uv1_hub() ? uv_num_possible_blades() : (uv_num_possible_blades() + 1) / 2, uv_num_possible_blades()); @@ -794,6 +929,7 @@ void __init uv_system_init(void) uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; spin_lock_init(&uv_blade_info[blade].nmi_lock); + min_pnode = min(pnode, min_pnode); max_pnode = max(pnode, max_pnode); blade++; } @@ -856,7 +992,7 @@ void __init uv_system_init(void) map_gru_high(max_pnode); map_mmr_high(max_pnode); - map_mmioh_high(max_pnode & pnode_io_mask); + map_mmioh_high(min_pnode, max_pnode); uv_cpu_init(); uv_scir_register_cpu_notifier(); -- cgit v1.2.2 From 166df91daf38f619d4ca90b58ff90983de6e40d2 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 11 Feb 2013 15:22:15 +0100 Subject: x86, head_32: Remove i386 pieces Remove code fragments detecting a 386 CPU since we don't support those anymore. Also, do not do alignment checks because they're done only at CPL3. Also, no need to preserve EFLAGS. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1360592538-10643-2-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 22 +++++----------------- 1 file changed, 5 insertions(+), 17 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c8932c79e78b..a9c5cc851285 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -394,30 +394,21 @@ default_entry: jz 1f # Did we do this already? call *%eax 1: - -/* check if it is 486 or 386. */ + /* - * XXX - this does a lot of unnecessary setup. Alignment checks don't - * apply at our cpl of 0 and the stack ought to be aligned already, and - * we don't need to preserve eflags. + * Check if it is 486 */ movl $-1,X86_CPUID # -1 for no CPUID initially - movb $3,X86 # at least 386 + movb $4,X86 # at least 486 pushfl # push EFLAGS popl %eax # get EFLAGS movl %eax,%ecx # save original EFLAGS - xorl $0x240000,%eax # flip AC and ID bits in EFLAGS + xorl $0x200000,%eax # flip ID bit in EFLAGS pushl %eax # copy to EFLAGS popfl # set EFLAGS pushfl # get new EFLAGS popl %eax # put it in eax xorl %ecx,%eax # change in flags - pushl %ecx # restore original EFLAGS - popfl - testl $0x40000,%eax # check if AC bit changed - je is386 - - movb $4,X86 # at least 486 testl $0x200000,%eax # check if ID bit changed je is486 @@ -445,10 +436,7 @@ default_entry: movl %edx,X86_CAPABILITY is486: movl $0x50022,%ecx # set AM, WP, NE and MP - jmp 2f - -is386: movl $2,%ecx # set MP -2: movl %cr0,%eax + movl %cr0,%eax andl $0x80000011,%eax # Save PG,PE,ET orl %ecx,%eax movl %eax,%cr0 -- cgit v1.2.2 From 9efb58de919efa8312861d454be014094f6f0ffc Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 11 Feb 2013 15:22:16 +0100 Subject: x86: Detect CPUID support early at boot We detect CPUID function support on each CPU and save it for later use, obviating the need to play the toggle EFLAGS.ID game every time. C code is looking at ->cpuid_level anyway. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1360592538-10643-3-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 50 +++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index a9c5cc851285..e3725a0f4327 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -307,30 +307,39 @@ default_entry: movl %eax,%cr0 /* - * New page tables may be in 4Mbyte page mode and may - * be using the global pages. + * We want to start out with EFLAGS unambiguously cleared. Some BIOSes leave + * bits like NT set. This would confuse the debugger if this code is traced. So + * initialize them properly now before switching to protected mode. That means + * DF in particular (even though we have cleared it earlier after copying the + * command line) because GCC expects it. + */ + pushl $0 + popfl + +/* + * New page tables may be in 4Mbyte page mode and may 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 - * and has flags other than the FPU flag set. + * NOTE! If we are on a 486 we may have no cr4 at all! Specifically, cr4 exists + * if and only if CPUID exists and has flags other than the FPU flag set. */ + movl $-1,pa(X86_CPUID) # preset CPUID level movl $X86_EFLAGS_ID,%ecx pushl %ecx - popfl - pushfl - popl %eax - pushl $0 - popfl + popfl # set EFLAGS=ID pushfl - popl %edx - xorl %edx,%eax - testl %ecx,%eax - jz 6f # No ID flag = no CPUID = no CR4 + popl %eax # get EFLAGS + testl $X86_EFLAGS_ID,%eax # did EFLAGS.ID remained set? + jz 6f # hw disallowed setting of ID bit + # which means no CPUID and no CR4 + + xorl %eax,%eax + cpuid + movl %eax,pa(X86_CPUID) # save largest std CPUID function movl $1,%eax cpuid - andl $~1,%edx # Ignore CPUID.FPU - jz 6f # No flags or only CPUID.FPU = no CR4 + 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 @@ -377,14 +386,6 @@ default_entry: /* Shift the stack pointer to a virtual address */ addl $__PAGE_OFFSET, %esp -/* - * Initialize eflags. Some BIOS's leave bits like NT set. This would - * confuse the debugger if this code is traced. - * XXX - best to initialize before switching to protected mode. - */ - pushl $0 - popfl - /* * start system 32-bit setup. We need to re-do some of the things done * in 16-bit mode for the "real" operations. @@ -461,7 +462,6 @@ is486: movl $0x50022,%ecx # set AM, WP, NE and MP xorl %eax,%eax # Clear LDT lldt %ax - cld # gcc2 wants the direction flag cleared at all times pushl $0 # fake return address for unwinder jmp *(initial_code) -- cgit v1.2.2 From c3a22a26d07d928e2b74b58e2f9d2436958620f0 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 11 Feb 2013 15:22:17 +0100 Subject: x86, head_32: Remove second CPUID detection from default_entry We do that once earlier now and cache it into new_cpu_data.cpuid_level so no need for the EFLAGS.ID toggling dance anymore. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1360592538-10643-4-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index e3725a0f4327..2e8532e7c80a 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -399,18 +399,7 @@ default_entry: /* * Check if it is 486 */ - movl $-1,X86_CPUID # -1 for no CPUID initially - movb $4,X86 # at least 486 - pushfl # push EFLAGS - popl %eax # get EFLAGS - movl %eax,%ecx # save original EFLAGS - xorl $0x200000,%eax # flip ID bit in EFLAGS - pushl %eax # copy to EFLAGS - popfl # set EFLAGS - pushfl # get new EFLAGS - popl %eax # put it in eax - xorl %ecx,%eax # change in flags - testl $0x200000,%eax # check if ID bit changed + cmpl $-1,X86_CPUID je is486 /* get vendor info */ @@ -436,7 +425,9 @@ default_entry: movb %cl,X86_MASK movl %edx,X86_CAPABILITY -is486: movl $0x50022,%ecx # set AM, WP, NE and MP +is486: + movb $4,X86 + movl $0x50022,%ecx # set AM, WP, NE and MP movl %cr0,%eax andl $0x80000011,%eax # Save PG,PE,ET orl %ecx,%eax -- cgit v1.2.2 From 5e2a044daf0c6f897eb69de931e3b29020e874a9 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 11 Feb 2013 15:22:18 +0100 Subject: x86, head_32: Give the 6 label a real name Jumping here we are about to enable paging so rename the label accordingly. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1360592538-10643-5-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 2e8532e7c80a..3c3f58a0808f 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -329,7 +329,7 @@ default_entry: pushfl popl %eax # get EFLAGS testl $X86_EFLAGS_ID,%eax # did EFLAGS.ID remained set? - jz 6f # hw disallowed setting of ID bit + jz enable_paging # hw disallowed setting of ID bit # which means no CPUID and no CR4 xorl %eax,%eax @@ -339,13 +339,13 @@ default_entry: movl $1,%eax cpuid andl $~1,%edx # Ignore CPUID.FPU - jz 6f # No flags or only CPUID.FPU = no CR4 + jz enable_paging # No flags or only CPUID.FPU = no CR4 movl pa(mmu_cr4_features),%eax movl %eax,%cr4 testb $X86_CR4_PAE, %al # check if PAE is enabled - jz 6f + jz enable_paging /* Check if extended functions are implemented */ movl $0x80000000, %eax @@ -353,7 +353,7 @@ default_entry: /* Value must be in the range 0x80000001 to 0x8000ffff */ subl $0x80000001, %eax cmpl $(0x8000ffff-0x80000001), %eax - ja 6f + ja enable_paging /* Clear bogus XD_DISABLE bits */ call verify_cpu @@ -362,7 +362,7 @@ default_entry: cpuid /* Execute Disable bit supported? */ btl $(X86_FEATURE_NX & 31), %edx - jnc 6f + jnc enable_paging /* Setup EFER (Extended Feature Enable Register) */ movl $MSR_EFER, %ecx @@ -372,7 +372,7 @@ default_entry: /* Make changes effective */ wrmsr -6: +enable_paging: /* * Enable paging -- cgit v1.2.2 From 32068f6527b8f1822a30671dedaf59c567325026 Mon Sep 17 00:00:00 2001 From: Olaf Hering <[mailto:olaf@aepfle.de]> Date: Sun, 3 Feb 2013 17:22:37 -0800 Subject: x86: Hyper-V: register clocksource only if its advertised Enable hyperv_clocksource only if its advertised as a feature. XenServer 6 returns the signature which is checked in ms_hyperv_platform(), but it does not offer all features. Currently the clocksource is enabled unconditionally in ms_hyperv_init_platform(), and the result is a hanging guest. Hyper-V spec Bit 1 indicates the availability of Partition Reference Counter. Register the clocksource only if this bit is set. The guest in question prints this in dmesg: [ 0.000000] Hypervisor detected: Microsoft HyperV [ 0.000000] HyperV: features 0x70, hints 0x0 This bug can be reproduced easily be setting 'viridian=1' in a HVM domU .cfg file. A workaround without this patch is to boot the HVM guest with 'clocksource=jiffies'. Signed-off-by: Olaf Hering Link: http://lkml.kernel.org/r/1359940959-32168-1-git-send-email-kys@microsoft.com Signed-off-by: K. Y. Srinivasan Cc: Cc: Greg KH Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mshyperv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 0a630dd4b620..646d192b18a2 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -68,7 +68,8 @@ static void __init ms_hyperv_init_platform(void) printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); - clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); + if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) + clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { -- cgit v1.2.2 From db34bbb767bdfa1ebed7214b876fe01c5b7ee457 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Sun, 3 Feb 2013 17:22:38 -0800 Subject: X86: Add a check to catch Xen emulation of Hyper-V Xen emulates Hyper-V to host enlightened Windows. Looks like this emulation may be turned on by default even for Linux guests. Check and fail Hyper-V detection if we are on Xen. [ hpa: the problem here is that Xen doesn't emulate Hyper-V well enough, and if the Xen support isn't compiled in, we end up stubling over the Hyper-V emulation and try to activate it -- and it fails. ] Signed-off-by: K. Y. Srinivasan Link: http://lkml.kernel.org/r/1359940959-32168-2-git-send-email-kys@microsoft.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mshyperv.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 646d192b18a2..4dab317f79b9 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -30,6 +30,13 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; + /* + * Xen emulates Hyper-V to support enlightened Windows. + * Check to see first if we are on a Xen Hypervisor. + */ + if (xen_cpuid_base()) + return false; + cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); -- cgit v1.2.2 From bc2b0331e077f576369a2b6c75d15ed4de4ef91f Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Sun, 3 Feb 2013 17:22:39 -0800 Subject: X86: Handle Hyper-V vmbus interrupts as special hypervisor interrupts Starting with win8, vmbus interrupts can be delivered on any VCPU in the guest and furthermore can be concurrently active on multiple VCPUs. Support this interrupt delivery model by setting up a separate IDT entry for Hyper-V vmbus. interrupts. I would like to thank Jan Beulich and Thomas Gleixner , for their help. In this version of the patch, based on the feedback, I have merged the IDT vector for Xen and Hyper-V and made the necessary adjustments. Furhermore, based on Jan's feedback I have added the necessary compilation switches. Signed-off-by: K. Y. Srinivasan Link: http://lkml.kernel.org/r/1359940959-32168-3-git-send-email-kys@microsoft.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mshyperv.c | 44 ++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/entry_32.S | 9 ++++++++- arch/x86/kernel/entry_64.S | 7 ++++++- 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 4dab317f79b9..a7d26d83fb70 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -14,10 +14,15 @@ #include #include #include +#include +#include #include #include #include #include +#include +#include +#include struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -77,6 +82,12 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); +#if IS_ENABLED(CONFIG_HYPERV) + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); +#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -85,3 +96,36 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .init_platform = ms_hyperv_init_platform, }; EXPORT_SYMBOL(x86_hyper_ms_hyperv); + +#if IS_ENABLED(CONFIG_HYPERV) +static int vmbus_irq = -1; +static irq_handler_t vmbus_isr; + +void hv_register_vmbus_handler(int irq, irq_handler_t handler) +{ + vmbus_irq = irq; + vmbus_isr = handler; +} + +void hyperv_vector_handler(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + struct irq_desc *desc; + + irq_enter(); + exit_idle(); + + desc = irq_to_desc(vmbus_irq); + + if (desc) + generic_handle_irq_desc(vmbus_irq, desc); + + irq_exit(); + set_irq_regs(old_regs); +} +#else +void hv_register_vmbus_handler(int irq, irq_handler_t handler) +{ +} +#endif +EXPORT_SYMBOL_GPL(hv_register_vmbus_handler); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 6ed91d9980e2..8831176aa5ef 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1091,11 +1091,18 @@ ENTRY(xen_failsafe_callback) _ASM_EXTABLE(4b,9b) ENDPROC(xen_failsafe_callback) -BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, xen_evtchn_do_upcall) #endif /* CONFIG_XEN */ +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index cb3c591339aa..048f2240f8e6 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1454,11 +1454,16 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) -apicinterrupt XEN_HVM_EVTCHN_CALLBACK \ +apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ xen_hvm_callback_vector xen_evtchn_do_upcall #endif /* CONFIG_XEN */ +#if IS_ENABLED(CONFIG_HYPERV) +apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ + hyperv_callback_vector hyperv_vector_handler +#endif /* CONFIG_HYPERV */ + /* * Some functions should be protected against kprobes */ -- cgit v1.2.2 From 6b59e366e074d3962e04f01efb8acc10a33c0e1e Mon Sep 17 00:00:00 2001 From: Satoru Takeuchi Date: Thu, 14 Feb 2013 09:07:35 +0900 Subject: x86, efi: remove duplicate code in setup_arch() by using, efi_is_native() The check, "IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)", in setup_arch() can be replaced by efi_is_enabled(). This change remove duplicate code and improve readability. Signed-off-by: Satoru Takeuchi Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Olof Johansson Signed-off-by: Matt Fleming --- arch/x86/kernel/setup.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 8b24289cc10c..1abb7969173a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1135,8 +1135,7 @@ void __init setup_arch(char **cmdline_p) * mismatched firmware/kernel archtectures since there is no * support for runtime services. */ - if (efi_enabled(EFI_BOOT) && - IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) { + if (efi_enabled(EFI_BOOT) && !efi_is_native()) { pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); } -- cgit v1.2.2 From 235b80226b986dabcbba844968f7807866bd0bfe Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 9 Nov 2012 23:51:47 -0500 Subject: x86: convert to ksignal Signed-off-by: Al Viro --- arch/x86/kernel/signal.c | 117 ++++++++++++++++++++++------------------------- 1 file changed, 54 insertions(+), 63 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d5b1f8a912ff..69562992e457 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -278,7 +278,7 @@ static const struct { }; static int -__setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, +__setup_frame(int sig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct sigframe __user *frame; @@ -286,7 +286,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, int err = 0; void __user *fpstate = NULL; - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; @@ -307,8 +307,8 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn); else restorer = &frame->retcode; - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; /* Set up to return from userspace. */ err |= __put_user(restorer, &frame->pretcode); @@ -327,7 +327,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, /* Set up registers for signal handler */ regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ka->sa.sa_handler; + regs->ip = (unsigned long)ksig->ka.sa.sa_handler; regs->ax = (unsigned long)sig; regs->dx = 0; regs->cx = 0; @@ -340,7 +340,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, return 0; } -static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, +static int __setup_rt_frame(int sig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; @@ -348,7 +348,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, int err = 0; void __user *fpstate = NULL; - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; @@ -368,8 +368,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); /* @@ -382,7 +382,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); } put_user_catch(err); - err |= copy_siginfo_to_user(&frame->info, info); + err |= copy_siginfo_to_user(&frame->info, &ksig->info); err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, regs, set->sig[0]); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); @@ -392,7 +392,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up registers for signal handler */ regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ka->sa.sa_handler; + regs->ip = (unsigned long)ksig->ka.sa.sa_handler; regs->ax = (unsigned long)sig; regs->dx = (unsigned long)&frame->info; regs->cx = (unsigned long)&frame->uc; @@ -405,20 +405,20 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; } #else /* !CONFIG_X86_32 */ -static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, +static int __setup_rt_frame(int sig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; void __user *fp = NULL; int err = 0; - frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp); + frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; - if (ka->sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user(&frame->info, info)) + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } @@ -434,8 +434,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up to return from userspace. If provided, use a stub already in userspace. */ /* x86-64 should always use SA_RESTORER. */ - if (ka->sa.sa_flags & SA_RESTORER) { - put_user_ex(ka->sa.sa_restorer, &frame->pretcode); + if (ksig->ka.sa.sa_flags & SA_RESTORER) { + put_user_ex(ksig->ka.sa.sa_restorer, &frame->pretcode); } else { /* could use a vstub here */ err |= -EFAULT; @@ -457,7 +457,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, next argument after the signal number on the stack. */ regs->si = (unsigned long)&frame->info; regs->dx = (unsigned long)&frame->uc; - regs->ip = (unsigned long) ka->sa.sa_handler; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; regs->sp = (unsigned long)frame; @@ -469,8 +469,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } #endif /* CONFIG_X86_32 */ -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, +static int x32_setup_rt_frame(struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs) { #ifdef CONFIG_X86_X32_ABI @@ -479,13 +479,13 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, int err = 0; void __user *fpstate = NULL; - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; - if (ka->sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user32(&frame->info, info)) + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, &ksig->info)) return -EFAULT; } @@ -499,8 +499,8 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, 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) { - restorer = ka->sa.sa_restorer; + if (ksig->ka.sa.sa_flags & SA_RESTORER) { + restorer = ksig->ka.sa.sa_restorer; } else { /* could use a vstub here */ restorer = NULL; @@ -518,10 +518,10 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* We use the x32 calling convention here... */ - regs->di = sig; + regs->di = ksig->sig; regs->si = (unsigned long) &frame->info; regs->dx = (unsigned long) &frame->uc; @@ -611,30 +611,29 @@ static int signr_convert(int sig) } static int -setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - struct pt_regs *regs) +setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { - int usig = signr_convert(sig); + int usig = signr_convert(ksig->sig); sigset_t *set = sigmask_to_save(); compat_sigset_t *cset = (compat_sigset_t *) set; /* Set up the stack frame */ if (is_ia32_frame()) { - if (ka->sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ka, info, cset, regs); + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + return ia32_setup_rt_frame(usig, ksig, cset, regs); else - return ia32_setup_frame(usig, ka, cset, regs); + return ia32_setup_frame(usig, ksig, cset, regs); } else if (is_x32_frame()) { - return x32_setup_rt_frame(usig, ka, info, cset, regs); + return x32_setup_rt_frame(ksig, cset, regs); } else { - return __setup_rt_frame(sig, ka, info, set, regs); + return __setup_rt_frame(ksig->sig, ksig, set, regs); } } static void -handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - struct pt_regs *regs) +handle_signal(struct ksignal *ksig, struct pt_regs *regs) { + bool failed; /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ @@ -645,7 +644,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, break; case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { + if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { regs->ax = -EINTR; break; } @@ -665,26 +664,21 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, likely(test_and_clear_thread_flag(TIF_FORCED_TF))) regs->flags &= ~X86_EFLAGS_TF; - if (setup_rt_frame(sig, ka, info, regs) < 0) { - force_sigsegv(sig, current); - return; + failed = (setup_rt_frame(ksig, regs) < 0); + if (!failed) { + /* + * Clear the direction flag as per the ABI for function entry. + */ + regs->flags &= ~X86_EFLAGS_DF; + /* + * Clear TF when entering the signal handler, but + * notify any tracer that was single-stepping it. + * The tracer may want to single-step inside the + * handler too. + */ + regs->flags &= ~X86_EFLAGS_TF; } - - /* - * Clear the direction flag as per the ABI for function entry. - */ - regs->flags &= ~X86_EFLAGS_DF; - - /* - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. - */ - regs->flags &= ~X86_EFLAGS_TF; - - signal_delivered(sig, info, ka, regs, - test_thread_flag(TIF_SINGLESTEP)); + signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } #ifdef CONFIG_X86_32 @@ -701,14 +695,11 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, */ static void do_signal(struct pt_regs *regs) { - struct k_sigaction ka; - siginfo_t info; - int signr; + struct ksignal ksig; - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - if (signr > 0) { + if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ - handle_signal(signr, &info, &ka, regs); + handle_signal(&ksig, regs); return; } -- cgit v1.2.2 From 19348e749e9515c429f5d561d2f2c724862a4bee Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 14 Feb 2013 15:14:02 -0500 Subject: x86: ptrace.c only needs export.h and not the full module.h Commit cb57a2b4cff7edf2a4e32c0163200e9434807e0a ("x86-32: Export kernel_stack_pointer() for modules") added an include of the module.h header in conjunction with adding an EXPORT_SYMBOL_GPL of kernel_stack_pointer. But module.h should be avoided for simple exports, since it in turn includes the world. Swap the module.h for export.h instead. Cc: Jiri Kosina Signed-off-by: Paul Gortmaker Link: http://lkml.kernel.org/r/1360872842-28417-1-git-send-email-paul.gortmaker@windriver.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b629bbe0d9bd..29a8120e6fe8 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.2 From 95c9608478d639dcffc14ea47b31bff021a99ed1 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 14 Feb 2013 14:02:52 -0800 Subject: x86, mm: Move reserving low memory later in initialization Move the reservation of low memory, except for the 4K which actually does belong to the BIOS, later in the initialization; in particular, after we have already reserved the trampoline. The current code locates the trampoline as high as possible, so by deferring the allocation we will still be able to reserve as much memory as is possible. This allows us to run with reservelow=640k without getting a crash on system startup. Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/n/tip-0y9dqmmsousf69wutxwl3kkf@git.kernel.org --- arch/x86/kernel/setup.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 8354399b3aae..0aebd776018e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -608,8 +608,6 @@ static __init void reserve_ibft_region(void) memblock_reserve(addr, size); } -static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; - static bool __init snb_gfx_workaround_needed(void) { #ifdef CONFIG_PCI @@ -698,8 +696,7 @@ static void __init trim_bios_range(void) * since some BIOSes are known to corrupt low memory. See the * Kconfig help text for X86_RESERVE_LOW. */ - e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE), - E820_RAM, E820_RESERVED); + e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); /* * special case: Some BIOSen report the PC BIOS @@ -711,6 +708,8 @@ static void __init trim_bios_range(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } +static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; + static int __init parse_reservelow(char *p) { unsigned long long size; @@ -733,6 +732,11 @@ static int __init parse_reservelow(char *p) early_param("reservelow", parse_reservelow); +static void __init trim_low_memory_range(void) +{ + memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -987,6 +991,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); trim_platform_memory_ranges(); + trim_low_memory_range(); init_gbpages(); -- cgit v1.2.2 From e259514eef764a5286873618e34c560ecb6cff13 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Wed, 6 Feb 2013 11:26:29 -0600 Subject: perf/x86/amd: Enable northbridge performance counters on AMD family 15h On AMD family 15h processors, there are 4 new performance counters (in addition to 6 core performance counters) that can be used for counting northbridge events (i.e. DRAM accesses). Their bit fields are almost identical to the core performance counters. However, unlike the core performance counters, these MSRs are shared between multiple cores (that share the same northbridge). We will reuse the same code path as existing family 10h northbridge event constraints handler logic to enforce this sharing. Signed-off-by: Jacob Shin Acked-by: Stephane Eranian Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Jacob Shin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1360171589-6381-7-git-send-email-jacob.shin@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_amd.c | 171 +++++++++++++++++++++++++++++++---- 1 file changed, 151 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 05462f0432d5..dfdab42aed27 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -132,11 +132,14 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } +static struct event_constraint *amd_nb_event_constraint; + /* * Previously calculated offsets */ static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly; static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; +static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; /* * Legacy CPUs: @@ -144,10 +147,14 @@ static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; * * CPUs with core performance counter extensions: * 6 counters starting at 0xc0010200 each offset by 2 + * + * CPUs with north bridge performance counter extensions: + * 4 additional counters starting at 0xc0010240 each offset by 2 + * (indexed right above either one of the above core counters) */ static inline int amd_pmu_addr_offset(int index, bool eventsel) { - int offset; + int offset, first, base; if (!index) return index; @@ -160,7 +167,23 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (!cpu_has_perfctr_core) + if (amd_nb_event_constraint && + test_bit(index, amd_nb_event_constraint->idxmsk)) { + /* + * calculate the offset of NB counters with respect to + * base eventsel or perfctr + */ + + first = find_first_bit(amd_nb_event_constraint->idxmsk, + X86_PMC_IDX_MAX); + + if (eventsel) + base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel; + else + base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr; + + offset = base + ((index - first) << 1); + } else if (!cpu_has_perfctr_core) offset = index; else offset = index << 1; @@ -175,24 +198,36 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) static inline int amd_pmu_rdpmc_index(int index) { - return index; -} + int ret, first; -static int amd_pmu_hw_config(struct perf_event *event) -{ - int ret; + if (!index) + return index; - /* pass precise event sampling to ibs: */ - if (event->attr.precise_ip && get_ibs_caps()) - return -ENOENT; + ret = rdpmc_indexes[index]; - ret = x86_pmu_hw_config(event); if (ret) return ret; - if (has_branch_stack(event)) - return -EOPNOTSUPP; + if (amd_nb_event_constraint && + test_bit(index, amd_nb_event_constraint->idxmsk)) { + /* + * according to the mnual, ECX value of the NB counters is + * the index of the NB counter (0, 1, 2 or 3) plus 6 + */ + + first = find_first_bit(amd_nb_event_constraint->idxmsk, + X86_PMC_IDX_MAX); + ret = index - first + 6; + } else + ret = index; + + rdpmc_indexes[index] = ret; + return ret; +} + +static int amd_core_hw_config(struct perf_event *event) +{ if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -206,10 +241,33 @@ static int amd_pmu_hw_config(struct perf_event *event) else if (event->attr.exclude_guest) event->hw.config |= AMD64_EVENTSEL_HOSTONLY; - if (event->attr.type != PERF_TYPE_RAW) - return 0; + return 0; +} - event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; +/* + * NB counters do not support the following event select bits: + * Host/Guest only + * Counter mask + * Invert counter mask + * Edge detect + * OS/User mode + */ +static int amd_nb_hw_config(struct perf_event *event) +{ + /* for NB, we only allow system wide counting mode */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; + + event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | + ARCH_PERFMON_EVENTSEL_OS); + + if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB | + ARCH_PERFMON_EVENTSEL_INT)) + return -EINVAL; return 0; } @@ -227,6 +285,11 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc) return (hwc->config & 0xe0) == 0xe0; } +static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc) +{ + return amd_nb_event_constraint && amd_is_nb_event(hwc); +} + static inline int amd_has_nb(struct cpu_hw_events *cpuc) { struct amd_nb *nb = cpuc->amd_nb; @@ -234,6 +297,30 @@ static inline int amd_has_nb(struct cpu_hw_events *cpuc) return nb && nb->nb_id != -1; } +static int amd_pmu_hw_config(struct perf_event *event) +{ + int ret; + + /* pass precise event sampling to ibs: */ + if (event->attr.precise_ip && get_ibs_caps()) + return -ENOENT; + + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + ret = x86_pmu_hw_config(event); + if (ret) + return ret; + + if (event->attr.type == PERF_TYPE_RAW) + event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; + + if (amd_is_perfctr_nb_event(&event->hw)) + return amd_nb_hw_config(event); + + return amd_core_hw_config(event); +} + static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -254,6 +341,19 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, } } +static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc) +{ + int core_id = cpu_data(smp_processor_id()).cpu_core_id; + + /* deliver interrupts only to this core */ + if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) { + hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE; + hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK; + hwc->config |= (u64)(core_id) << + AMD64_EVENTSEL_INT_CORE_SEL_SHIFT; + } +} + /* * AMD64 NorthBridge events need special treatment because * counter access needs to be synchronized across all cores @@ -299,6 +399,12 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev struct perf_event *old; int idx, new = -1; + if (!c) + c = &unconstrained; + + if (cpuc->is_fake) + return c; + /* * detect if already present, if so reuse * @@ -335,6 +441,9 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev if (new == -1) return &emptyconstraint; + if (amd_is_perfctr_nb_event(hwc)) + amd_nb_interrupt_hw_config(hwc); + return &nb->event_constraints[new]; } @@ -434,7 +543,8 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))) return &unconstrained; - return __amd_get_nb_event_constraints(cpuc, event, &unconstrained); + return __amd_get_nb_event_constraints(cpuc, event, + amd_nb_event_constraint); } static void amd_put_event_constraints(struct cpu_hw_events *cpuc, @@ -533,6 +643,9 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); +static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0); +static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0); + static struct event_constraint * amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -598,8 +711,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev return &amd_f15_PMC20; } case AMD_EVENT_NB: - /* not yet implemented */ - return &emptyconstraint; + return __amd_get_nb_event_constraints(cpuc, event, + amd_nb_event_constraint); default: return &emptyconstraint; } @@ -647,7 +760,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int setup_event_constraints(void) { - if (boot_cpu_data.x86 >= 0x15) + if (boot_cpu_data.x86 == 0x15) x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; return 0; } @@ -677,6 +790,23 @@ static int setup_perfctr_core(void) return 0; } +static int setup_perfctr_nb(void) +{ + if (!cpu_has_perfctr_nb) + return -ENODEV; + + x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB; + + if (cpu_has_perfctr_core) + amd_nb_event_constraint = &amd_NBPMC96; + else + amd_nb_event_constraint = &amd_NBPMC74; + + printk(KERN_INFO "perf: AMD northbridge performance counters detected\n"); + + return 0; +} + __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -687,6 +817,7 @@ __init int amd_pmu_init(void) setup_event_constraints(); setup_perfctr_core(); + setup_perfctr_nb(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, -- cgit v1.2.2 From dd8af076262cc1ff85a8d5e0c5b1a4716d19fe25 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sat, 9 Feb 2013 21:10:04 -0500 Subject: APM idle: register apm_cpu_idle via cpuidle Update APM to register its local idle routine with cpuidle. This allows us to stop exporting pm_idle to modules on x86. The Kconfig sub-option, APM_CPU_IDLE, now depends on on CPU_IDLE. Compile-tested only. Signed-off-by: Len Brown Reviewed-by: Daniel Lezcano Cc: Jiri Kosina --- arch/x86/kernel/apm_32.c | 57 ++++++++++++++++++++++++++++------------------- arch/x86/kernel/process.c | 3 --- 2 files changed, 34 insertions(+), 26 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index d65464e43503..9f4bc6a1164d 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -232,6 +232,7 @@ #include #include #include +#include #include #include @@ -360,13 +361,35 @@ struct apm_user { * idle percentage above which bios idle calls are done */ #ifdef CONFIG_APM_CPU_IDLE -#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012 #define DEFAULT_IDLE_THRESHOLD 95 #else #define DEFAULT_IDLE_THRESHOLD 100 #endif #define DEFAULT_IDLE_PERIOD (100 / 3) +static int apm_cpu_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index); + +static struct cpuidle_driver apm_idle_driver = { + .name = "apm_idle", + .owner = THIS_MODULE, + .en_core_tk_irqen = 1, + .states = { + { /* entry 0 is for polling */ }, + { /* entry 1 is for APM idle */ + .name = "APM", + .desc = "APM idle", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 250, /* WAG */ + .target_residency = 500, /* WAG */ + .enter = &apm_cpu_idle + }, + }, + .state_count = 2, +}; + +static struct cpuidle_device apm_cpuidle_device; + /* * Local variables */ @@ -377,7 +400,6 @@ static struct { static int clock_slowed; static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD; static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD; -static int set_pm_idle; static int suspends_pending; static int standbys_pending; static int ignore_sys_suspend; @@ -884,8 +906,6 @@ static void apm_do_busy(void) #define IDLE_CALC_LIMIT (HZ * 100) #define IDLE_LEAKY_MAX 16 -static void (*original_pm_idle)(void) __read_mostly; - /** * apm_cpu_idle - cpu idling for APM capable Linux * @@ -894,7 +914,8 @@ static void (*original_pm_idle)(void) __read_mostly; * Furthermore it calls the system default idle routine. */ -static void apm_cpu_idle(void) +static int apm_cpu_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ @@ -904,7 +925,6 @@ static void apm_cpu_idle(void) unsigned int jiffies_since_last_check = jiffies - last_jiffies; unsigned int bucket; - WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; @@ -950,10 +970,7 @@ recalc: break; } } - if (original_pm_idle) - original_pm_idle(); - else - default_idle(); + default_idle(); local_irq_disable(); jiffies_since_last_check = jiffies - last_jiffies; if (jiffies_since_last_check > idle_period) @@ -963,7 +980,7 @@ recalc: if (apm_idle_done) apm_do_busy(); - local_irq_enable(); + return index; } /** @@ -2381,9 +2398,9 @@ static int __init apm_init(void) if (HZ != 100) idle_period = (idle_period * HZ) / 100; if (idle_threshold < 100) { - original_pm_idle = pm_idle; - pm_idle = apm_cpu_idle; - set_pm_idle = 1; + if (!cpuidle_register_driver(&apm_idle_driver)) + if (cpuidle_register_device(&apm_cpuidle_device)) + cpuidle_unregister_driver(&apm_idle_driver); } return 0; @@ -2393,15 +2410,9 @@ static void __exit apm_exit(void) { int error; - if (set_pm_idle) { - pm_idle = original_pm_idle; - /* - * We are about to unload the current idle thread pm callback - * (pm_idle), Wait for all processors to update cached/local - * copies of pm_idle before proceeding. - */ - kick_all_cpus_sync(); - } + cpuidle_unregister_device(&apm_cpuidle_device); + cpuidle_unregister_driver(&apm_idle_driver); + if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0) && (apm_info.connection_version > 0x0100)) { error = apm_engage_power_management(APM_DEVICE_ALL, 0); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2ed787f15bf0..f571a6e08710 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -272,9 +272,6 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); -#ifdef CONFIG_APM_MODULE -EXPORT_SYMBOL(pm_idle); -#endif #ifndef CONFIG_SMP static inline void play_dead(void) -- cgit v1.2.2 From a476bda30baf7efa7f305793a340aae07b6e5780 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sat, 9 Feb 2013 21:45:03 -0500 Subject: x86 idle: rename global pm_idle to static x86_idle (pm_idle)() is being removed from linux/pm.h because Linux does not have such a cross-architecture concept. x86 uses an idle function pointer in its architecture specific code as a backup to cpuidle. So we re-name x86 use of pm_idle to x86_idle, and make it static to x86. Signed-off-by: Len Brown Cc: x86@kernel.org --- arch/x86/kernel/process.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f571a6e08710..ceb05db59be1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -268,10 +268,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); +static void (*x86_idle)(void); #ifndef CONFIG_SMP static inline void play_dead(void) @@ -348,7 +345,7 @@ void cpu_idle(void) rcu_idle_enter(); if (cpuidle_idle_call()) - pm_idle(); + x86_idle(); rcu_idle_exit(); start_critical_timings(); @@ -395,9 +392,9 @@ EXPORT_SYMBOL(default_idle); bool set_pm_idle_to_default(void) { - bool ret = !!pm_idle; + bool ret = !!x86_idle; - pm_idle = default_idle; + x86_idle = default_idle; return ret; } @@ -564,11 +561,10 @@ static void amd_e400_idle(void) void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (pm_idle == poll_idle && smp_num_siblings > 1) { + if (x86_idle == poll_idle && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); - } #endif - if (pm_idle) + if (x86_idle) return; if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { @@ -576,19 +572,19 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) * One CPU supports mwait => All CPUs supports mwait */ pr_info("using mwait in idle threads\n"); - pm_idle = mwait_idle; + x86_idle = mwait_idle; } else if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); - pm_idle = amd_e400_idle; + x86_idle = amd_e400_idle; } else - pm_idle = default_idle; + x86_idle = default_idle; } void __init init_amd_e400_c1e_mask(void) { /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */ - if (pm_idle == amd_e400_idle) + if (x86_idle == amd_e400_idle) zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL); } @@ -599,7 +595,7 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { pr_info("using polling idle threads\n"); - pm_idle = poll_idle; + x86_idle = poll_idle; boot_option_idle_override = IDLE_POLL; } else if (!strcmp(str, "mwait")) { boot_option_idle_override = IDLE_FORCE_MWAIT; @@ -612,7 +608,7 @@ static int __init idle_setup(char *str) * To continue to load the CPU idle driver, don't touch * the boot_option_idle_override. */ - pm_idle = default_idle; + x86_idle = default_idle; boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { /* -- cgit v1.2.2 From 52d3d06e706bdde3d6c5c386deb065c3b4c51618 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 19 Feb 2013 19:33:12 +0100 Subject: x86, cpu, amd: Fix WC+ workaround for older virtual hosts The WC+ workaround for F10h introduces a new MSR and kvm host #GPs on accesses to unknown MSRs if paravirt is not compiled in. Use the exception-handling MSR accessors so as not to break 3.8 and later guests booting on older hosts. Remove a redundant family check while at it. Cc: Gleb Natapov Cc: Boris Ostrovsky Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1361298793-31834-1-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/amd.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 721ef3208eb5..163af4a91d09 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -723,12 +723,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) * performance degradation for certain nested-paging guests. * Prevent this conversion by clearing bit 24 in * MSR_AMD64_BU_CFG2. + * + * NOTE: we want to use the _safe accessors so as not to #GP kvm + * guests on older kvm hosts. */ - if (c->x86 == 0x10) { - rdmsrl(MSR_AMD64_BU_CFG2, value); - value &= ~(1ULL << 24); - wrmsrl(MSR_AMD64_BU_CFG2, value); - } + + rdmsrl_safe(MSR_AMD64_BU_CFG2, &value); + value &= ~(1ULL << 24); + wrmsrl_safe(MSR_AMD64_BU_CFG2, value); } rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); -- cgit v1.2.2 From 69943182bb9e19e4b60ea5033f683ec1af1703a9 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 20 Feb 2013 11:15:12 +0100 Subject: perf/x86: Add Intel IvyBridge event scheduling constraints Intel IvyBridge processor has different constraints compared to SandyBridge. Therefore it needs its own contraint table. This patch adds the constraint table. Without this patch, the events listed in the patch may not be scheduled correctly and bogus counts may be collected. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1361355312-3323-1-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 4914e94ad6e8..529c8931fc02 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -107,6 +107,27 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_ivb_event_constraints[] __read_mostly = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */ + INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ + INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), @@ -2095,7 +2116,7 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_snb(); - x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; x86_pmu.extra_regs = intel_snb_extra_regs; -- cgit v1.2.2 From 27cf929845b10043f2257693c7d179a9e0b1980e Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Tue, 19 Feb 2013 20:47:07 +0100 Subject: x86/apic: Fix parsing of the 'lapic' cmdline option Including " lapic " in the kernel cmdline on an x86-64 kernel makes it panic while parsing early params -- e.g. with no user visible output. Fix this bug by ensuring arg is non-NULL before passing it to strncmp(). Reported-by: PaX Team Signed-off-by: Mathias Krause Acked-by: David Rientjes Cc: Suresh Siddha Link: http://lkml.kernel.org/r/1361303227-13174-1-git-send-email-minipli@googlemail.com Cc: stable@vger.kernel.org # v3.8 Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a5b4dce1b7ac..904611bf0e5a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -131,7 +131,7 @@ 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)) + else if (arg && !strncmp(arg, "notscdeadline", 13)) setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return 0; } -- cgit v1.2.2 From ac630dd98a47b60b27d716758d5f4276cb974662 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 22 Feb 2013 13:09:51 -0800 Subject: x86-64: don't set the early IDT to point directly to 'early_idt_handler' The code requires the use of the proper per-exception-vector stub functions (set up as the early_idt_handlers[] array - note the 's') that make sure to set up the error vector number. This is true regardless of whether CONFIG_EARLY_PRINTK is set or not. Why? The stack offset for the comparison of __KERNEL_CS won't be right otherwise, nor will the new check (from commit 8170e6bed465: "x86, 64bit: Use a #PF handler to materialize early mappings on demand") for the page fault exception vector. Acked-by: H. Peter Anvin Signed-off-by: Linus Torvalds --- arch/x86/kernel/head64.c | 7 +------ arch/x86/kernel/head_64.S | 2 ++ 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 57334f4cd3af..2590025e52c2 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -159,13 +159,8 @@ void __init x86_64_start_kernel(char * real_mode_data) /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { -#ifdef CONFIG_EARLY_PRINTK + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) set_intr_gate(i, &early_idt_handlers[i]); -#else - set_intr_gate(i, early_idt_handler); -#endif - } load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d94f6d68be2a..b7de3b25adb5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -336,6 +336,7 @@ early_idt_handlers: i = i + 1 .endr +/* This is global to keep gas from relaxing the jumps */ ENTRY(early_idt_handler) cld @@ -404,6 +405,7 @@ ENTRY(early_idt_handler) addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) INTERRUPT_RETURN +ENDPROC(early_idt_handler) __INITDATA -- cgit v1.2.2 From 496ad9aa8ef448058e36ca7a787c61f2e63f0f54 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 23 Jan 2013 17:07:38 -0500 Subject: new helper: file_inode(file) Signed-off-by: Al Viro --- arch/x86/kernel/cpuid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 60c78917190c..1e4dbcfe6d31 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -85,7 +85,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, { char __user *tmp = buf; struct cpuid_regs cmd; - int cpu = iminor(file->f_path.dentry->d_inode); + int cpu = iminor(file_inode(file)); u64 pos = *ppos; ssize_t bytes = 0; int err = 0; @@ -116,7 +116,7 @@ static int cpuid_open(struct inode *inode, struct file *file) unsigned int cpu; struct cpuinfo_x86 *c; - cpu = iminor(file->f_path.dentry->d_inode); + cpu = iminor(file_inode(file)); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ -- cgit v1.2.2 From c4c605246452d0e578945ea95a8e72877e97e8c6 Mon Sep 17 00:00:00 2001 From: Wen Congyang Date: Fri, 22 Feb 2013 16:33:24 -0800 Subject: cpu_hotplug: clear apicid to node when the cpu is hotremoved When a cpu is hotpluged, we call acpi_map_cpu2node() in _acpi_map_lsapic() to store the cpu's node and apicid's node. But we don't clear the cpu's node in acpi_unmap_lsapic() when this cpu is hotremoved. If the node is also hotremoved, we will get the following messages: kernel BUG at include/linux/gfp.h:329! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat xt_CHECKSUM iptable_mangle bridge stp llc sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel microcode pcspkr i2c_i801 i2c_core lpc_ich mfd_core ioatdma e1000e i7core_edac edac_core sg acpi_memhotplug igb dca sd_mod crc_t10dif megaraid_sas mptsas mptscsih mptbase scsi_transport_sas scsi_mod Pid: 3126, comm: init Not tainted 3.6.0-rc3-tangchen-hostbridge+ #13 FUJITSU-SV PRIMEQUEST 1800E/SB RIP: 0010:[] [] allocate_slab+0x28d/0x300 RSP: 0018:ffff88078a049cf8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000001 RDI: 0000000000000246 RBP: ffff88078a049d38 R08: 00000000000040d0 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000b5f R12: 00000000000052d0 R13: ffff8807c1417300 R14: 0000000000030038 R15: 0000000000000003 FS: 00007fa9b1b44700(0000) GS:ffff8807c3800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fa9b09acca0 CR3: 000000078b855000 CR4: 00000000000007e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process init (pid: 3126, threadinfo ffff88078a048000, task ffff8807bb6f2650) Call Trace: new_slab+0x30/0x1b0 __slab_alloc+0x358/0x4c0 kmem_cache_alloc_node_trace+0xb4/0x1e0 alloc_fair_sched_group+0xd0/0x1b0 sched_create_group+0x3e/0x110 sched_autogroup_create_attach+0x4d/0x180 sys_setsid+0xd4/0xf0 system_call_fastpath+0x16/0x1b Code: 89 c4 e9 73 fe ff ff 31 c0 89 de 48 c7 c7 45 de 9e 81 44 89 45 c8 e8 22 05 4b 00 85 db 44 8b 45 c8 0f 89 4f ff ff ff 0f 0b eb fe <0f> 0b 90 eb fd 0f 0b eb fe 89 de 48 c7 c7 45 de 9e 81 31 c0 44 RIP [] allocate_slab+0x28d/0x300 RSP ---[ end trace adf84c90f3fea3e5 ]--- The reason is that the cpu's node is not NUMA_NO_NODE, we will call alloc_pages_exact_node() to alloc memory on the node, but the node is offlined. If the node is onlined, we still need cpu's node. For example: a task on the cpu is sleeped when the cpu is hotremoved. We will choose another cpu to run this task when it is waked up. If we know the cpu's node, we will choose the cpu on the same node first. So we should clear cpu-to-node mapping when the node is offlined. This patch only clears apicid-to-node mapping when the cpu is hotremoved. [akpm@linux-foundation.org: fix section error] Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Cc: Yasuaki Ishimatsu Cc: David Rientjes Cc: Jiang Liu Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/acpi/boot.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index cfc755dc1607..230c8ea878e5 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -696,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { +#ifdef CONFIG_ACPI_NUMA + set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); +#endif + per_cpu(x86_cpu_to_apicid, cpu) = -1; set_cpu_present(cpu, false); num_processors--; -- cgit v1.2.2 From e8d1955258091e4c92d5a975ebd7fd8a98f5d30f Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:44 -0800 Subject: acpi, memory-hotplug: parse SRAT before memblock is ready On linux, the pages used by kernel could not be migrated. As a result, if a memory range is used by kernel, it cannot be hot-removed. So if we want to hot-remove memory, we should prevent kernel from using it. The way now used to prevent this is specify a memory range by movablemem_map boot option and set it as ZONE_MOVABLE. But when the system is booting, memblock will allocate memory, and reserve the memory for kernel. And before we parse SRAT, and know the node memory ranges, memblock is working. And it may allocate memory in ranges to be set as ZONE_MOVABLE. This memory can be used by kernel, and never be freed. So, let's parse SRAT before memblock is called first. And it is early enough. The first call of memblock_find_in_range_node() is in: setup_arch() |-->setup_real_mode() so, this patch add a function early_parse_srat() to parse SRAT, and call it before setup_real_mode() is called. NOTE: 1) early_parse_srat() is called before numa_init(), and has initialized numa_meminfo. So DO NOT clear numa_nodes_parsed in numa_init() and DO NOT zero numa_meminfo in numa_init(), otherwise we will lose memory numa info. 2) I don't know why using count of memory affinities parsed from SRAT as a return value in original acpi_numa_init(). So I add a static variable srat_mem_cnt to remember this count and use it as the return value of the new acpi_numa_init() [mhocko@suse.cz: parse SRAT before memblock is ready fix] Signed-off-by: Tang Chen Reviewed-by: Wen Congyang Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Len Brown Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 915f5efefcf5..9c857f05cef0 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1056,6 +1056,15 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif + /* + * In the memory hotplug case, the kernel needs info from SRAT to + * determine which memory is hotpluggable before allocating memory + * using memblock. + */ + acpi_boot_table_init(); + early_acpi_boot_init(); + early_parse_srat(); + #ifdef CONFIG_X86_32 printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped< Date: Mon, 25 Feb 2013 15:54:10 -0500 Subject: x86, doc: Fix incorrect comment about 64-bit code segment descriptors The AMD64 Architecture Programmer's Manual Volume 2, on page 89 mentions: "If the processor is running in 64-bit mode (L=1), the only valid setting of the D bit is 0." This matches with what the code does. Signed-off-by: Konrad Rzeszutek Wilk Link: http://lkml.kernel.org/r/1361825650-14031-4-git-send-email-konrad.wilk@oracle.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 980053c4b9cc..37f5304e80f5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -49,7 +49,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) startup_64: /* - * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1, + * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table * for us. These identity mapped page tables map all of the * kernel pages and possibly all of memory. @@ -146,7 +146,7 @@ ident_complete: jmp secondary_startup_64 ENTRY(secondary_startup_64) /* - * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1, + * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. * * %esi holds a physical pointer to real_mode_data. -- cgit v1.2.2 From 7c10093692ed2e6f318387d96b829320aa0ca64c Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 27 Feb 2013 12:46:40 -0800 Subject: x86: Make sure we can boot in the case the BDA contains pure garbage On non-BIOS platforms it is possible that the BIOS data area contains garbage instead of being zeroed or something equivalent (firmware people: we are talking of 1.5K here, so please do the sane thing.) We need on the order of 20-30K of low memory in order to boot, which may grow up to < 64K in the future. We probably want to avoid the lowest of the low memory. At the same time, it seems extremely unlikely that a legitimate EBDA would ever reach down to the 128K (which would require it to be over half a megabyte in size.) Thus, pick 128K as the cutoff for "this is insane, ignore." We may still end up reserving a bunch of extra memory on the low megabyte, but that is not really a major issue these days. In the worst case we lose 512K of RAM. This code really should be merged with trim_bios_range() in arch/x86/kernel/setup.c, but that is a bigger patch for a later merge window. Reported-by: Darren Hart Signed-off-by: H. Peter Anvin Cc: Matt Fleming Cc: Link: http://lkml.kernel.org/n/tip-oebml055yyfm8yxmria09rja@git.kernel.org --- arch/x86/kernel/head.c | 53 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 34 insertions(+), 19 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index 48d9d4ea1020..992f442ca155 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -5,8 +5,6 @@ #include #include -#define BIOS_LOWMEM_KILOBYTES 0x413 - /* * The BIOS places the EBDA/XBDA at the top of conventional * memory, and usually decreases the reported amount of @@ -16,17 +14,30 @@ * chipset: reserve a page before VGA to prevent PCI prefetch * into it (errata #56). Usually the page is reserved anyways, * unless you have no PS/2 mouse plugged in. + * + * This functions is deliberately very conservative. Losing + * memory in the bottom megabyte is rarely a problem, as long + * as we have enough memory to install the trampoline. Using + * memory that is in use by the BIOS or by some DMA device + * the BIOS didn't shut down *is* a big problem. */ + +#define BIOS_LOWMEM_KILOBYTES 0x413 +#define LOWMEM_CAP 0x9f000U /* Absolute maximum */ +#define INSANE_CUTOFF 0x20000U /* Less than this = insane */ + void __init reserve_ebda_region(void) { unsigned int lowmem, ebda_addr; - /* To determine the position of the EBDA and the */ - /* end of conventional memory, we need to look at */ - /* the BIOS data area. In a paravirtual environment */ - /* that area is absent. We'll just have to assume */ - /* that the paravirt case can handle memory setup */ - /* correctly, without our help. */ + /* + * To determine the position of the EBDA and the + * end of conventional memory, we need to look at + * the BIOS data area. In a paravirtual environment + * that area is absent. We'll just have to assume + * that the paravirt case can handle memory setup + * correctly, without our help. + */ if (paravirt_enabled()) return; @@ -37,19 +48,23 @@ void __init reserve_ebda_region(void) /* start of EBDA area */ ebda_addr = get_bios_ebda(); - /* Fixup: bios puts an EBDA in the top 64K segment */ - /* of conventional memory, but does not adjust lowmem. */ - if ((lowmem - ebda_addr) <= 0x10000) - lowmem = ebda_addr; + /* + * Note: some old Dells seem to need 4k EBDA without + * reporting so, so just consider the memory above 0x9f000 + * to be off limits (bugzilla 2990). + */ + + /* If the EBDA address is below 128K, assume it is bogus */ + if (ebda_addr < INSANE_CUTOFF) + ebda_addr = LOWMEM_CAP; - /* Fixup: bios does not report an EBDA at all. */ - /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */ - if ((ebda_addr == 0) && (lowmem >= 0x9f000)) - lowmem = 0x9f000; + /* If lowmem is less than 128K, assume it is bogus */ + if (lowmem < INSANE_CUTOFF) + lowmem = LOWMEM_CAP; - /* Paranoia: should never happen, but... */ - if ((lowmem == 0) || (lowmem >= 0x100000)) - lowmem = 0x9f000; + /* Use the lower of the lowmem and EBDA markers as the cutoff */ + lowmem = min(lowmem, ebda_addr); + lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */ /* reserve all memory between lowmem and the 1MB mark */ memblock_reserve(lowmem, 0x100000 - lowmem); -- cgit v1.2.2 From 6131ffaa1f091415b7a24abb01f033d9c0a727f4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Feb 2013 16:59:05 -0500 Subject: more file_inode() open-coded instances Signed-off-by: Al Viro --- arch/x86/kernel/msr.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 4929502c1372..ce130493b802 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -71,7 +71,7 @@ static ssize_t msr_read(struct file *file, char __user *buf, u32 __user *tmp = (u32 __user *) buf; u32 data[2]; u32 reg = *ppos; - int cpu = iminor(file->f_path.dentry->d_inode); + int cpu = iminor(file_inode(file)); int err = 0; ssize_t bytes = 0; @@ -99,7 +99,7 @@ static ssize_t msr_write(struct file *file, const char __user *buf, const u32 __user *tmp = (const u32 __user *)buf; u32 data[2]; u32 reg = *ppos; - int cpu = iminor(file->f_path.dentry->d_inode); + int cpu = iminor(file_inode(file)); int err = 0; ssize_t bytes = 0; @@ -125,7 +125,7 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) { u32 __user *uregs = (u32 __user *)arg; u32 regs[8]; - int cpu = iminor(file->f_path.dentry->d_inode); + int cpu = iminor(file_inode(file)); int err; switch (ioc) { @@ -171,13 +171,12 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) static int msr_open(struct inode *inode, struct file *file) { - unsigned int cpu; + unsigned int cpu = iminor(file_inode(file)); struct cpuinfo_x86 *c; if (!capable(CAP_SYS_RAWIO)) return -EPERM; - cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ -- cgit v1.2.2 From b67bfe0d42cac56c512dd5da4b1b347a23f4b70a Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 27 Feb 2013 17:06:00 -0800 Subject: hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin Acked-by: Paul E. McKenney Signed-off-by: Sasha Levin Cc: Wu Fengguang Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/kprobes/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e124554598ee..3f06e6149981 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -652,7 +652,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; @@ -682,7 +682,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -701,7 +701,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_assert(ri, orig_ret_address, trampoline_address); correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -728,7 +728,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } -- cgit v1.2.2 From 3d2a80a230250c2534ce5b17503670adaf1d7fff Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 27 Feb 2013 15:28:28 -0500 Subject: x86/kvm: Fix pvclock vsyscall fixmap The physical memory fixmapped for the pvclock clock_gettime vsyscall was allocated, and thus is not a kernel symbol. __pa() is the proper method to use in this case. Fixes the crash below when booting a next-20130204+ smp guest on a 3.8-rc5+ KVM host. [ 0.666410] udevd[97]: starting version 175 [ 0.674043] udevd[97]: udevd:[97]: segfault at ffffffffff5fd020 ip 00007fff069e277f sp 00007fff068c9ef8 error d Acked-by: Marcelo Tosatti Signed-off-by: Peter Hurley Signed-off-by: Gleb Natapov --- arch/x86/kernel/pvclock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 85c39590c1a4..2cb9470ea85b 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -185,7 +185,7 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_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), + __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } -- cgit v1.2.2 From 20e6926dcbafa1b361f1c29d967688be14b6ca4b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 1 Mar 2013 14:51:27 -0800 Subject: x86, ACPI, mm: Revert movablemem_map support Tim found: WARNING: at arch/x86/kernel/smpboot.c:324 topology_sane.isra.2+0x6f/0x80() Hardware name: S2600CP sched: CPU #1's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency. smpboot: Booting Node 1, Processors #1 Modules linked in: Pid: 0, comm: swapper/1 Not tainted 3.9.0-0-generic #1 Call Trace: set_cpu_sibling_map+0x279/0x449 start_secondary+0x11d/0x1e5 Don Morris reproduced on a HP z620 workstation, and bisected it to commit e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") It turns out movable_map has some problems, and it breaks several things 1. numa_init is called several times, NOT just for srat. so those nodes_clear(numa_nodes_parsed) memset(&numa_meminfo, 0, sizeof(numa_meminfo)) can not be just removed. Need to consider sequence is: numaq, srat, amd, dummy. and make fall back path working. 2. simply split acpi_numa_init to early_parse_srat. a. that early_parse_srat is NOT called for ia64, so you break ia64. b. for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE) still left in numa_init. So it will just clear result from early_parse_srat. it should be moved before that.... c. it breaks ACPI_TABLE_OVERIDE...as the acpi table scan is moved early before override from INITRD is settled. 3. that patch TITLE is total misleading, there is NO x86 in the title, but it changes critical x86 code. It caused x86 guys did not pay attention to find the problem early. Those patches really should be routed via tip/x86/mm. 4. after that commit, following range can not use movable ram: a. real_mode code.... well..funny, legacy Node0 [0,1M) could be hot-removed? b. initrd... it will be freed after booting, so it could be on movable... c. crashkernel for kdump...: looks like we can not put kdump kernel above 4G anymore. d. init_mem_mapping: can not put page table high anymore. e. initmem_init: vmemmap can not be high local node anymore. That is not good. If node is hotplugable, the mem related range like page table and vmemmap could be on the that node without problem and should be on that node. We have workaround patch that could fix some problems, but some can not be fixed. So just remove that offending commit and related ones including: f7210e6c4ac7 ("mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region().") 01a178a94e8e ("acpi, memory-hotplug: support getting hotplug info from SRAT") 27168d38fa20 ("acpi, memory-hotplug: extend movablemem_map ranges to the end of node") e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") fb06bc8e5f42 ("page_alloc: bootmem limit with movablecore_map") 42f47e27e761 ("page_alloc: make movablemem_map have higher priority") 6981ec31146c ("page_alloc: introduce zone_movable_limit[] to keep movable limit for nodes") 34b71f1e04fc ("page_alloc: add movable_memmap kernel parameter") 4d59a75125d5 ("x86: get pg_data_t's memory from other node") Later we should have patches that will make sure kernel put page table and vmemmap on local node ram instead of push them down to node0. Also need to find way to put other kernel used ram to local node ram. Reported-by: Tim Gardner Reported-by: Don Morris Bisected-by: Don Morris Tested-by: Don Morris Signed-off-by: Yinghai Lu Cc: Tony Luck Cc: Thomas Renninger Cc: Tejun Heo Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e89acdf6b77b..84d32855f65c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1056,15 +1056,6 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif - /* - * In the memory hotplug case, the kernel needs info from SRAT to - * determine which memory is hotpluggable before allocating memory - * using memblock. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); - early_parse_srat(); - #ifdef CONFIG_X86_32 printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped<