linux_dsm_epyc7002/drivers/cpufreq/powernow-k8.h

223 lines
7.5 KiB
C
Raw Normal View History

/*
* (c) 2003-2006 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*/
[CPUFREQ] powernow-k8: ignore out-of-range PstateStatus value A workaround for AMD CPU family 11h erratum 311 might cause that the P-state Status Register shows a "current P-state" which is larger than the "current P-state limit" in P-state Current Limit Register. For the wrong P-state value there is no ACPI _PSS object defined and powernow-k8/cpufreq can't determine the proper CPU frequency for that state. As a consequence this can cause a panic during boot (potentially with all recent kernel versions -- at least I have reproduced it with various 2.6.27 kernels and with the current .28 series), as an example: powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82 processors (2 \ ) powernow-k8: 0 : pstate 0 (2200 MHz) powernow-k8: 1 : pstate 1 (1100 MHz) powernow-k8: 2 : pstate 2 (600 MHz) BUG: unable to handle kernel paging request at ffff88086e7528b8 IP: [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f PGD 202063 PUD 0 Oops: 0002 [#1] SMP last sysfs file: CPU 1 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.28-rc3-dirty #16 RIP: 0010:[<ffffffff80486361>] [<ffffffff80486361>] cpufreq_stats_update+0x4a/0\ f Synaptics claims to have extended capabilities, but I'm not able to read them.<6\ 6 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88006e7528c0 RDX: 00000000ffffffff RSI: ffff88006e54af00 RDI: ffffffff808f056c RBP: 00000000fffee697 R08: 0000000000000003 R09: ffff88006e73f080 R10: 0000000000000001 R11: 00000000002191c0 R12: ffff88006fb83c10 R13: 00000000ffffffff R14: 0000000000000001 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88006fb50740(0000) knlGS:0000000000000000 Unable to initialize Synaptics hardware. CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: ffff88086e7528b8 CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff88006fb82000, task ffff88006fb816d0) Stack: ffff88006e74da50 0000000000000000 ffff88006e54af00 ffffffff804863c7 ffff88006e74da50 0000000000000000 00000000ffffffff 0000000000000000 ffff88006fb83c10 ffffffff8024b46c ffffffff808f0560 ffff88006fb83c10 Call Trace: [<ffffffff804863c7>] ? cpufreq_stat_notifier_trans+0x51/0x83 [<ffffffff8024b46c>] ? notifier_call_chain+0x29/0x4c [<ffffffff8024b561>] ? __srcu_notifier_call_chain+0x46/0x61 [<ffffffff8048496d>] ? cpufreq_notify_transition+0x93/0xa9 [<ffffffff8021ab8d>] ? powernowk8_target+0x1e8/0x5f3 [<ffffffff80486687>] ? cpufreq_governor_performance+0x1b/0x20 [<ffffffff80484886>] ? __cpufreq_governor+0x71/0xa8 [<ffffffff80484b21>] ? __cpufreq_set_policy+0x101/0x13e [<ffffffff80485bcd>] ? cpufreq_add_dev+0x3f0/0x4cd [<ffffffff8048577a>] ? handle_update+0x0/0x8 [<ffffffff803c2062>] ? sysdev_driver_register+0xb6/0x10d [<ffffffff8056592c>] ? powernowk8_init+0x0/0x7e [<ffffffff8048604c>] ? cpufreq_register_driver+0x8f/0x140 [<ffffffff80209056>] ? _stext+0x56/0x14f [<ffffffff802c2234>] ? proc_register+0x122/0x17d [<ffffffff802c23a0>] ? create_proc_entry+0x73/0x8a [<ffffffff8025c259>] ? register_irq_proc+0x92/0xaa [<ffffffff8025c2c8>] ? init_irq_proc+0x57/0x69 [<ffffffff807fc85f>] ? kernel_init+0x116/0x169 [<ffffffff8020cc79>] ? child_rip+0xa/0x11 [<ffffffff807fc749>] ? kernel_init+0x0/0x169 [<ffffffff8020cc6f>] ? child_rip+0x0/0x11 Code: 05 c5 83 36 00 48 c7 c2 48 5d 86 80 48 8b 04 d8 48 8b 40 08 48 8b 34 02 48\ RIP [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f RSP <ffff88006fb83b20> CR2: ffff88086e7528b8 ---[ end trace 0678bac75e67a2f7 ]--- Kernel panic - not syncing: Attempted to kill init! In short, aftereffect of the wrong P-state is that cpufreq_stats_update() uses "-1" as index for some array in cpufreq_stats_update (unsigned int cpu) { ... if (stat->time_in_state) stat->time_in_state[stat->last_index] = cputime64_add(stat->time_in_state[stat->last_index], cputime_sub(cur_time, stat->last_time)); ... } Fortunately, the wrong P-state value is returned only if the core is in P-state 0. This fix solves the problem by detecting the out-of-range P-state, ignoring it, and using "0" instead. Cc: Mark Langsdorf <mark.langsdorf@amd.com> Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com> Signed-off-by: Dave Jones <davej@redhat.com>
2008-11-21 20:49:25 +07:00
enum pstate {
HW_PSTATE_INVALID = 0xff,
HW_PSTATE_0 = 0,
HW_PSTATE_1 = 1,
HW_PSTATE_2 = 2,
HW_PSTATE_3 = 3,
HW_PSTATE_4 = 4,
HW_PSTATE_5 = 5,
HW_PSTATE_6 = 6,
HW_PSTATE_7 = 7,
};
struct powernow_k8_data {
unsigned int cpu;
u32 numps; /* number of p-states */
u32 batps; /* number of p-states supported on battery */
u32 max_hw_pstate; /* maximum legal hardware pstate */
/* these values are constant when the PSB is used to determine
* vid/fid pairings, but are modified during the ->target() call
* when ACPI is used */
u32 rvo; /* ramp voltage offset */
u32 irt; /* isochronous relief time */
u32 vidmvs; /* usable value calculated from mvs */
u32 vstable; /* voltage stabilization time, units 20 us */
u32 plllock; /* pll lock time, units 1 us */
u32 exttype; /* extended interface = 1 */
/* keep track of the current fid / vid or pstate */
[CPUFREQ] powernow-k8: ignore out-of-range PstateStatus value A workaround for AMD CPU family 11h erratum 311 might cause that the P-state Status Register shows a "current P-state" which is larger than the "current P-state limit" in P-state Current Limit Register. For the wrong P-state value there is no ACPI _PSS object defined and powernow-k8/cpufreq can't determine the proper CPU frequency for that state. As a consequence this can cause a panic during boot (potentially with all recent kernel versions -- at least I have reproduced it with various 2.6.27 kernels and with the current .28 series), as an example: powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82 processors (2 \ ) powernow-k8: 0 : pstate 0 (2200 MHz) powernow-k8: 1 : pstate 1 (1100 MHz) powernow-k8: 2 : pstate 2 (600 MHz) BUG: unable to handle kernel paging request at ffff88086e7528b8 IP: [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f PGD 202063 PUD 0 Oops: 0002 [#1] SMP last sysfs file: CPU 1 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.28-rc3-dirty #16 RIP: 0010:[<ffffffff80486361>] [<ffffffff80486361>] cpufreq_stats_update+0x4a/0\ f Synaptics claims to have extended capabilities, but I'm not able to read them.<6\ 6 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88006e7528c0 RDX: 00000000ffffffff RSI: ffff88006e54af00 RDI: ffffffff808f056c RBP: 00000000fffee697 R08: 0000000000000003 R09: ffff88006e73f080 R10: 0000000000000001 R11: 00000000002191c0 R12: ffff88006fb83c10 R13: 00000000ffffffff R14: 0000000000000001 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88006fb50740(0000) knlGS:0000000000000000 Unable to initialize Synaptics hardware. CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: ffff88086e7528b8 CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff88006fb82000, task ffff88006fb816d0) Stack: ffff88006e74da50 0000000000000000 ffff88006e54af00 ffffffff804863c7 ffff88006e74da50 0000000000000000 00000000ffffffff 0000000000000000 ffff88006fb83c10 ffffffff8024b46c ffffffff808f0560 ffff88006fb83c10 Call Trace: [<ffffffff804863c7>] ? cpufreq_stat_notifier_trans+0x51/0x83 [<ffffffff8024b46c>] ? notifier_call_chain+0x29/0x4c [<ffffffff8024b561>] ? __srcu_notifier_call_chain+0x46/0x61 [<ffffffff8048496d>] ? cpufreq_notify_transition+0x93/0xa9 [<ffffffff8021ab8d>] ? powernowk8_target+0x1e8/0x5f3 [<ffffffff80486687>] ? cpufreq_governor_performance+0x1b/0x20 [<ffffffff80484886>] ? __cpufreq_governor+0x71/0xa8 [<ffffffff80484b21>] ? __cpufreq_set_policy+0x101/0x13e [<ffffffff80485bcd>] ? cpufreq_add_dev+0x3f0/0x4cd [<ffffffff8048577a>] ? handle_update+0x0/0x8 [<ffffffff803c2062>] ? sysdev_driver_register+0xb6/0x10d [<ffffffff8056592c>] ? powernowk8_init+0x0/0x7e [<ffffffff8048604c>] ? cpufreq_register_driver+0x8f/0x140 [<ffffffff80209056>] ? _stext+0x56/0x14f [<ffffffff802c2234>] ? proc_register+0x122/0x17d [<ffffffff802c23a0>] ? create_proc_entry+0x73/0x8a [<ffffffff8025c259>] ? register_irq_proc+0x92/0xaa [<ffffffff8025c2c8>] ? init_irq_proc+0x57/0x69 [<ffffffff807fc85f>] ? kernel_init+0x116/0x169 [<ffffffff8020cc79>] ? child_rip+0xa/0x11 [<ffffffff807fc749>] ? kernel_init+0x0/0x169 [<ffffffff8020cc6f>] ? child_rip+0x0/0x11 Code: 05 c5 83 36 00 48 c7 c2 48 5d 86 80 48 8b 04 d8 48 8b 40 08 48 8b 34 02 48\ RIP [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f RSP <ffff88006fb83b20> CR2: ffff88086e7528b8 ---[ end trace 0678bac75e67a2f7 ]--- Kernel panic - not syncing: Attempted to kill init! In short, aftereffect of the wrong P-state is that cpufreq_stats_update() uses "-1" as index for some array in cpufreq_stats_update (unsigned int cpu) { ... if (stat->time_in_state) stat->time_in_state[stat->last_index] = cputime64_add(stat->time_in_state[stat->last_index], cputime_sub(cur_time, stat->last_time)); ... } Fortunately, the wrong P-state value is returned only if the core is in P-state 0. This fix solves the problem by detecting the out-of-range P-state, ignoring it, and using "0" instead. Cc: Mark Langsdorf <mark.langsdorf@amd.com> Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com> Signed-off-by: Dave Jones <davej@redhat.com>
2008-11-21 20:49:25 +07:00
u32 currvid;
u32 currfid;
enum pstate currpstate;
/* the powernow_table includes all frequency and vid/fid pairings:
* fid are the lower 8 bits of the index, vid are the upper 8 bits.
* frequency is in kHz */
struct cpufreq_frequency_table *powernow_table;
/* the acpi table needs to be kept. it's only available if ACPI was
* used to determine valid frequency/vid/fid states */
struct acpi_processor_performance acpi_data;
/* we need to keep track of associated cores, but let cpufreq
* handle hotplug events - so just point at cpufreq pol->cpus
* structure */
struct cpumask *available_cores;
};
/* processor's cpuid instruction support */
#define CPUID_PROCESSOR_SIGNATURE 1 /* function 1 */
#define CPUID_XFAM 0x0ff00000 /* extended family */
#define CPUID_XFAM_K8 0
#define CPUID_XMOD 0x000f0000 /* extended model */
#define CPUID_XMOD_REV_MASK 0x000c0000
#define CPUID_XFAM_10H 0x00100000 /* family 0x10 */
#define CPUID_USE_XFAM_XMOD 0x00000f00
#define CPUID_GET_MAX_CAPABILITIES 0x80000000
#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007
#define P_STATE_TRANSITION_CAPABLE 6
/* Model Specific Registers for p-state transitions. MSRs are 64-bit. For */
/* writes (wrmsr - opcode 0f 30), the register number is placed in ecx, and */
/* the value to write is placed in edx:eax. For reads (rdmsr - opcode 0f 32), */
/* the register number is placed in ecx, and the data is returned in edx:eax. */
#define MSR_FIDVID_CTL 0xc0010041
#define MSR_FIDVID_STATUS 0xc0010042
/* Field definitions within the FID VID Low Control MSR : */
#define MSR_C_LO_INIT_FID_VID 0x00010000
#define MSR_C_LO_NEW_VID 0x00003f00
#define MSR_C_LO_NEW_FID 0x0000003f
#define MSR_C_LO_VID_SHIFT 8
/* Field definitions within the FID VID High Control MSR : */
#define MSR_C_HI_STP_GNT_TO 0x000fffff
/* Field definitions within the FID VID Low Status MSR : */
#define MSR_S_LO_CHANGE_PENDING 0x80000000 /* cleared when completed */
#define MSR_S_LO_MAX_RAMP_VID 0x3f000000
#define MSR_S_LO_MAX_FID 0x003f0000
#define MSR_S_LO_START_FID 0x00003f00
#define MSR_S_LO_CURRENT_FID 0x0000003f
/* Field definitions within the FID VID High Status MSR : */
#define MSR_S_HI_MIN_WORKING_VID 0x3f000000
#define MSR_S_HI_MAX_WORKING_VID 0x003f0000
#define MSR_S_HI_START_VID 0x00003f00
#define MSR_S_HI_CURRENT_VID 0x0000003f
#define MSR_C_HI_STP_GNT_BENIGN 0x00000001
/* Hardware Pstate _PSS and MSR definitions */
#define USE_HW_PSTATE 0x00000080
#define HW_PSTATE_MASK 0x00000007
#define HW_PSTATE_VALID_MASK 0x80000000
#define HW_PSTATE_MAX_MASK 0x000000f0
#define HW_PSTATE_MAX_SHIFT 4
#define MSR_PSTATE_DEF_BASE 0xc0010064 /* base of Pstate MSRs */
#define MSR_PSTATE_STATUS 0xc0010063 /* Pstate Status MSR */
#define MSR_PSTATE_CTRL 0xc0010062 /* Pstate control MSR */
#define MSR_PSTATE_CUR_LIMIT 0xc0010061 /* pstate current limit MSR */
/* define the two driver architectures */
#define CPU_OPTERON 0
#define CPU_HW_PSTATE 1
/*
* There are restrictions frequencies have to follow:
* - only 1 entry in the low fid table ( <=1.4GHz )
* - lowest entry in the high fid table must be >= 2 * the entry in the
* low fid table
* - lowest entry in the high fid table must be a <= 200MHz + 2 * the entry
* in the low fid table
* - the parts can only step at <= 200 MHz intervals, odd fid values are
* supported in revision G and later revisions.
* - lowest frequency must be >= interprocessor hypertransport link speed
* (only applies to MP systems obviously)
*/
/* fids (frequency identifiers) are arranged in 2 tables - lo and hi */
#define LO_FID_TABLE_TOP 7 /* fid values marking the boundary */
#define HI_FID_TABLE_BOTTOM 8 /* between the low and high tables */
#define LO_VCOFREQ_TABLE_TOP 1400 /* corresponding vco frequency values */
#define HI_VCOFREQ_TABLE_BOTTOM 1600
#define MIN_FREQ_RESOLUTION 200 /* fids jump by 2 matching freq jumps by 200 */
#define MAX_FID 0x2a /* Spec only gives FID values as far as 5 GHz */
#define LEAST_VID 0x3e /* Lowest (numerically highest) useful vid value */
#define MIN_FREQ 800 /* Min and max freqs, per spec */
#define MAX_FREQ 5000
#define INVALID_FID_MASK 0xffffffc0 /* not a valid fid if these bits are set */
#define INVALID_VID_MASK 0xffffffc0 /* not a valid vid if these bits are set */
#define VID_OFF 0x3f
#define STOP_GRANT_5NS 1 /* min poss memory access latency for voltage change */
#define PLL_LOCK_CONVERSION (1000/5) /* ms to ns, then divide by clock period */
#define MAXIMUM_VID_STEPS 1 /* Current cpus only allow a single step of 25mV */
#define VST_UNITS_20US 20 /* Voltage Stabilization Time is in units of 20us */
/*
* Most values of interest are encoded in a single field of the _PSS
* entries: the "control" value.
*/
#define IRT_SHIFT 30
#define RVO_SHIFT 28
#define EXT_TYPE_SHIFT 27
#define PLL_L_SHIFT 20
#define MVS_SHIFT 18
#define VST_SHIFT 11
#define VID_SHIFT 6
#define IRT_MASK 3
#define RVO_MASK 3
#define EXT_TYPE_MASK 1
#define PLL_L_MASK 0x7f
#define MVS_MASK 3
#define VST_MASK 0x7f
#define VID_MASK 0x1f
#define FID_MASK 0x1f
#define EXT_VID_MASK 0x3f
#define EXT_FID_MASK 0x3f
/*
* Version 1.4 of the PSB table. This table is constructed by BIOS and is
* to tell the OS's power management driver which VIDs and FIDs are
* supported by this particular processor.
* If the data in the PSB / PST is wrong, then this driver will program the
* wrong values into hardware, which is very likely to lead to a crash.
*/
#define PSB_ID_STRING "AMDK7PNOW!"
#define PSB_ID_STRING_LEN 10
#define PSB_VERSION_1_4 0x14
struct psb_s {
u8 signature[10];
u8 tableversion;
u8 flags1;
u16 vstable;
u8 flags2;
u8 num_tables;
u32 cpuid;
u8 plllocktime;
u8 maxfid;
u8 maxvid;
u8 numps;
};
/* Pairs of fid/vid values are appended to the version 1.4 PSB table. */
struct pst_s {
u8 fid;
u8 vid;
};
static int core_voltage_pre_transition(struct powernow_k8_data *data,
u32 reqvid, u32 regfid);
static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid);
static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);
static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index);
static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);