x86: cpumask: update 32-bit APM not to mug current->cpus_allowed

Impact: cleanup, avoid cpumask games

The APM code wants to run on CPU 0: we create an "on_cpu0" wrapper
which uses work_on_cpu() if we're not already on cpu 0.

This introduces a new failure mode: -ENOMEM, so we add an explicit
err arg and handle Linux-style errnos in apm_err().

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
LKML-Reference: <200903111631.29787.rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 145 insertions, 103 deletions

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 10033fe718e0..c1941be9fb17 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -466,7 +466,7 @@ static const lookup_t error_table[] = {
  *      @err: APM BIOS return code
  *
  *      Write a meaningful log entry to the kernel log in the event of
- *      an APM error.
+ *      an APM error.  Note that this also handles (negative) kernel errors.
  */
 
 static void apm_error(char *str, int err)
@@ -478,43 +478,14 @@ static void apm_error(char *str, int err)
                         break;
         if (i < ERROR_COUNT)
                 printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
+        else if (err < 0)
+                printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err);
         else
                 printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
                        str, err);
 }
 
 /*
- * Lock APM functionality to physical CPU 0
- */
-
-#ifdef CONFIG_SMP
-
-static cpumask_t apm_save_cpus(void)
-{
-        cpumask_t x = current->cpus_allowed;
-        /* Some bioses don't like being called from CPU != 0 */
-        set_cpus_allowed(current, cpumask_of_cpu(0));
-        BUG_ON(smp_processor_id() != 0);
-        return x;
-}
-
-static inline void apm_restore_cpus(cpumask_t mask)
-{
-        set_cpus_allowed(current, mask);
-}
-
-#else
-
-/*
- *      No CPU lockdown needed on a uniprocessor
- */
-
-#define apm_save_cpus()         (current->cpus_allowed)
-#define apm_restore_cpus(x)     (void)(x)
-
-#endif
-
-/*
  * These are the actual BIOS calls.  Depending on APM_ZERO_SEGS and
  * apm_info.allow_ints, we are being really paranoid here!  Not only
  * are interrupts disabled, but all the segment registers (except SS)
@@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags)
 #       define APM_DO_RESTORE_SEGS
 #endif
 
+struct apm_bios_call {
+        u32 func;
+        /* In and out */
+        u32 ebx;
+        u32 ecx;
+        /* Out only */
+        u32 eax;
+        u32 edx;
+        u32 esi;
+
+        /* Error: -ENOMEM, or bits 8-15 of eax */
+        int err;
+};
+
 /**
- *      apm_bios_call   -       Make an APM BIOS 32bit call
- *      @func: APM function to execute
- *      @ebx_in: EBX register for call entry
- *      @ecx_in: ECX register for call entry
- *      @eax: EAX register return
- *      @ebx: EBX register return
- *      @ecx: ECX register return
- *      @edx: EDX register return
- *      @esi: ESI register return
+ *      __apm_bios_call - Make an APM BIOS 32bit call
+ *      @_call: pointer to struct apm_bios_call.
  *
  *      Make an APM call using the 32bit protected mode interface. The
  *      caller is responsible for knowing if APM BIOS is configured and
@@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags)
  *      flag is loaded into AL.  If there is an error, then the error
  *      code is returned in AH (bits 8-15 of eax) and this function
  *      returns non-zero.
+ *
+ *      Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
-        u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
+static long __apm_bios_call(void *_call)
 {
         APM_DECL_SEGS
         unsigned long           flags;
-        cpumask_t               cpus;
         int                     cpu;
         struct desc_struct      save_desc_40;
         struct desc_struct      *gdt;
-
-        cpus = apm_save_cpus();
+        struct apm_bios_call    *call = _call;
 
         cpu = get_cpu();
+        BUG_ON(cpu != 0);
         gdt = get_cpu_gdt_table(cpu);
         save_desc_40 = gdt[0x40 / 8];
         gdt[0x40 / 8] = bad_bios_desc;
 
         apm_irq_save(flags);
         APM_DO_SAVE_SEGS;
-        apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
+        apm_bios_call_asm(call->func, call->ebx, call->ecx,
+                          &call->eax, &call->ebx, &call->ecx, &call->edx,
+                          &call->esi);
         APM_DO_RESTORE_SEGS;
         apm_irq_restore(flags);
         gdt[0x40 / 8] = save_desc_40;
         put_cpu();
-        apm_restore_cpus(cpus);
 
-        return *eax & 0xff;
+        return call->eax & 0xff;
+}
+
+/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */
+static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call)
+{
+        int ret;
+
+        /* Don't bother with work_on_cpu in the common case, so we don't
+         * have to worry about OOM or overhead. */
+        if (get_cpu() == 0) {
+                ret = fn(call);
+                put_cpu();
+        } else {
+                put_cpu();
+                ret = work_on_cpu(0, fn, call);
+        }
+
+        /* work_on_cpu can fail with -ENOMEM */
+        if (ret < 0)
+                call->err = ret;
+        else
+                call->err = (call->eax >> 8) & 0xff;
+
+        return ret;
 }
 
 /**
- *      apm_bios_call_simple    -       make a simple APM BIOS 32bit call
- *      @func: APM function to invoke
- *      @ebx_in: EBX register value for BIOS call
- *      @ecx_in: ECX register value for BIOS call
- *      @eax: EAX register on return from the BIOS call
+ *      apm_bios_call   -       Make an APM BIOS 32bit call (on CPU 0)
+ *      @call: the apm_bios_call registers.
+ *
+ *      If there is an error, it is returned in @call.err.
+ */
+static int apm_bios_call(struct apm_bios_call *call)
+{
+        return on_cpu0(__apm_bios_call, call);
+}
+
+/**
+ *      __apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0)
+ *      @_call: pointer to struct apm_bios_call.
  *
  *      Make a BIOS call that returns one value only, or just status.
  *      If there is an error, then the error code is returned in AH
- *      (bits 8-15 of eax) and this function returns non-zero. This is
- *      used for simpler BIOS operations. This call may hold interrupts
- *      off for a long time on some laptops.
+ *      (bits 8-15 of eax) and this function returns non-zero (it can
+ *      also return -ENOMEM). This is used for simpler BIOS operations.
+ *      This call may hold interrupts off for a long time on some laptops.
+ *
+ *      Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
+static long __apm_bios_call_simple(void *_call)
 {
         u8                      error;
         APM_DECL_SEGS
         unsigned long           flags;
-        cpumask_t               cpus;
         int                     cpu;
         struct desc_struct      save_desc_40;
         struct desc_struct      *gdt;
-
-        cpus = apm_save_cpus();
+        struct apm_bios_call    *call = _call;
 
         cpu = get_cpu();
+        BUG_ON(cpu != 0);
         gdt = get_cpu_gdt_table(cpu);
         save_desc_40 = gdt[0x40 / 8];
         gdt[0x40 / 8] = bad_bios_desc;
 
         apm_irq_save(flags);
         APM_DO_SAVE_SEGS;
-        error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
+        error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
+                                         &call->eax);
         APM_DO_RESTORE_SEGS;
         apm_irq_restore(flags);
         gdt[0x40 / 8] = save_desc_40;
         put_cpu();
-        apm_restore_cpus(cpus);
         return error;
 }
 
 /**
+ *      apm_bios_call_simple    -       make a simple APM BIOS 32bit call
+ *      @func: APM function to invoke
+ *      @ebx_in: EBX register value for BIOS call
+ *      @ecx_in: ECX register value for BIOS call
+ *      @eax: EAX register on return from the BIOS call
+ *      @err: bits
+ *
+ *      Make a BIOS call that returns one value only, or just status.
+ *      If there is an error, then the error code is returned in @err
+ *      and this function returns non-zero. This is used for simpler
+ *      BIOS operations.  This call may hold interrupts off for a long
+ *      time on some laptops.
+ */
+static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax,
+                                int *err)
+{
+        struct apm_bios_call call;
+        int ret;
+
+        call.func = func;
+        call.ebx = ebx_in;
+        call.ecx = ecx_in;
+
+        ret = on_cpu0(__apm_bios_call_simple, &call);
+        *eax = call.eax;
+        *err = call.err;
+        return ret;
+}
+
+/**
  *      apm_driver_version      -       APM driver version
  *      @val:   loaded with the APM version on return
  *
@@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
 static int apm_driver_version(u_short *val)
 {
         u32 eax;
+        int err;
 
-        if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
-                return (eax >> 8) & 0xff;
+        if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err))
+                return err;
         *val = eax;
         return APM_SUCCESS;
 }
@@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val)
  *      that APM 1.2 is in use. If no messges are pending the value 0x80
  *      is returned (No power management events pending).
  */
-
 static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 {
-        u32 eax;
-        u32 ebx;
-        u32 ecx;
-        u32 dummy;
+        struct apm_bios_call call;
 
-        if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
-                          &dummy, &dummy))
-                return (eax >> 8) & 0xff;
-        *event = ebx;
+        call.func = APM_FUNC_GET_EVENT;
+        call.ebx = call.ecx = 0;
+
+        if (apm_bios_call(&call))
+                return call.err;
+
+        *event = call.ebx;
         if (apm_info.connection_version < 0x0102)
                 *info = ~0; /* indicate info not valid */
         else
-                *info = ecx;
+                *info = call.ecx;
         return APM_SUCCESS;
 }
 
@@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 static int set_power_state(u_short what, u_short state)
 {
         u32 eax;
+        int err;
 
-        if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
-                return (eax >> 8) & 0xff;
+        if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err))
+                return err;
         return APM_SUCCESS;
 }
 
@@ -770,6 +811,7 @@ static int apm_do_idle(void)
         u8 ret = 0;
         int idled = 0;
         int polling;
+        int err;
 
         polling = !!(current_thread_info()->status & TS_POLLING);
         if (polling) {
@@ -782,7 +824,7 @@ static int apm_do_idle(void)
         }
         if (!need_resched()) {
                 idled = 1;
-                ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
+                ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err);
         }
         if (polling)
                 current_thread_info()->status |= TS_POLLING;
@@ -797,8 +839,7 @@ static int apm_do_idle(void)
                  * Only report the failure the first 5 times.
                  */
                 if (++t < 5) {
-                        printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
-                               (eax >> 8) & 0xff);
+                        printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err);
                         t = jiffies;
                 }
                 return -1;
@@ -816,9 +857,10 @@ static int apm_do_idle(void)
 static void apm_do_busy(void)
 {
         u32 dummy;
+        int err;
 
         if (clock_slowed || ALWAYS_CALL_BUSY) {
-                (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
+                (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err);
                 clock_slowed = 0;
         }
 }
@@ -937,7 +979,7 @@ static void apm_power_off(void)
 
         /* Some bioses don't like being called from CPU != 0 */
         if (apm_info.realmode_power_off) {
-                (void)apm_save_cpus();
+                set_cpus_allowed_ptr(current, cpumask_of(0));
                 machine_real_restart(po_bios_call, sizeof(po_bios_call));
         } else {
                 (void)set_system_power_state(APM_STATE_OFF);
@@ -956,12 +998,13 @@ static void apm_power_off(void)
 static int apm_enable_power_management(int enable)
 {
         u32 eax;
+        int err;
 
         if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
                 return APM_NOT_ENGAGED;
         if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
-                                 enable, &eax))
-                return (eax >> 8) & 0xff;
+                                 enable, &eax, &err))
+                return err;
         if (enable)
                 apm_info.bios.flags &= ~APM_BIOS_DISABLED;
         else
@@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable)
 
 static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
 {
-        u32 eax;
-        u32 ebx;
-        u32 ecx;
-        u32 edx;
-        u32 dummy;
+        struct apm_bios_call call;
+
+        call.func = APM_FUNC_GET_STATUS;
+        call.ebx = APM_DEVICE_ALL;
+        call.ecx = 0;
 
         if (apm_info.get_power_status_broken)
                 return APM_32_UNSUPPORTED;
-        if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
-                          &eax, &ebx, &ecx, &edx, &dummy))
-                return (eax >> 8) & 0xff;
-        *status = ebx;
-        *bat = ecx;
+        if (apm_bios_call(&call))
+                return call.err;
+        *status = call.ebx;
+        *bat = call.ecx;
         if (apm_info.get_power_status_swabinminutes) {
-                *life = swab16((u16)edx);
+                *life = swab16((u16)call.edx);
                 *life |= 0x8000;
         } else
-                *life = edx;
+                *life = call.edx;
         return APM_SUCCESS;
 }
 
@@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status,
 static int apm_engage_power_management(u_short device, int enable)
 {
         u32 eax;
+        int err;
 
         if ((enable == 0) && (device == APM_DEVICE_ALL)
             && (apm_info.bios.flags & APM_BIOS_DISABLED))
                 return APM_DISABLED;
-        if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax))
-                return (eax >> 8) & 0xff;
+        if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable,
+                                 &eax, &err))
+                return err;
         if (device == APM_DEVICE_ALL) {
                 if (enable)
                         apm_info.bios.flags &= ~APM_BIOS_DISENGAGED;
@@ -1682,16 +1726,14 @@ static int apm(void *unused)
         char            *power_stat;
         char            *bat_stat;
 
-#ifdef CONFIG_SMP
         /* 2002/08/01 - WT
          * This is to avoid random crashes at boot time during initialization
          * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D.
          * Some bioses don't like being called from CPU != 0.
          * Method suggested by Ingo Molnar.
          */
-        set_cpus_allowed(current, cpumask_of_cpu(0));
+        set_cpus_allowed_ptr(current, cpumask_of(0));
         BUG_ON(smp_processor_id() != 0);
-#endif
 
         if (apm_info.connection_version == 0) {
                 apm_info.connection_version = apm_info.bios.version;