[PATCH v8 5/6] alpha: decode Clipper environmental events

[Magnus Lindholm <linmag7@gmail.com>]

Restrict ES40 live environmental decoding to Clipper. Validate frame bounds
and string-table masks, and separate fault bits from status context.
Report valid notifications even when no recognized fault bits are set,
so door-closed and supply-return notifications remain visible. A single
status snapshot does not establish a recovery transition.

Keep SMIR bit 0 and inverted halt/reset bits as raw context. During the
ES40 PSU cable test, bit 0 remained set after the individual PSU failure
indication cleared. Its polarity/latching is unverified, so do not call
it a current PSU failure. Use mask 0x14 for the remaining SMIR faults.
Decode only QW1 through QW7 as live environmental status, as documented
in the ES40 Service Guide, Tables D-20 and D-21.

Use plain door-status messages. Preserve unknown or truncated frames
in bounded raw dumps. Firmware console-log scanning is independent of
the live environmental handler.

Signed-off-by: Magnus Lindholm <linmag7@gmail.com>
---
Changes since v7:
- Split console-log support into patch 6 so it can be reviewed separately.
- Make clipper_process_environment() void and remove its unused print
  parameter. Always print from the bit helper, retaining a boolean only
  to decide whether to report that no recognized faults are present.
- Keep version-history remarks here rather than in the commit message.

Changes since v6:
- Remove the redundant environmental silent pass, treat SMIR bit 0 as raw
  context, and retain only mask 0x14 for recognized SMIR faults.

 arch/alpha/kernel/err_tsunami.c | 221 ++++++++++++++++++++++++++++++++
 arch/alpha/kernel/proto.h       |   1 +
 arch/alpha/kernel/sys_dp264.c   |   2 +-
 3 files changed, 223 insertions(+), 1 deletion(-)

diff --git a/arch/alpha/kernel/err_tsunami.c b/arch/alpha/kernel/err_tsunami.c
index 03080d219cde..471d6888b9d4 100644
--- a/arch/alpha/kernel/err_tsunami.c
+++ b/arch/alpha/kernel/err_tsunami.c
@@ -263,3 +263,224 @@ tsunami_machine_check(unsigned long vector, unsigned long la_ptr)
 		mb();
 	}
 }
+
+static const char * const CLIPPER_EnvQW1SMIR[] = {
+	"", /* SMIR<0>: retain as raw context until its semantics are known. */
+	"OCP or RMC halt detected",
+	"Sys_DC_Notok failure detected",
+	"",
+	"System temperature over 50 degrees C failure",
+	"PCI Bus #0 is in reset",
+	"PCI Bus #1 is in reset",
+	"System is being reset"
+};
+
+static const char * const CLIPPER_EnvQW2CPUIR[] = {
+	"CPU0 regulator is enabled",
+	"CPU1 regulator is enabled",
+	"CPU2 regulator is enabled",
+	"CPU3 regulator is enabled",
+	"CPU0 regulator or configuration sequence fail",
+	"CPU1 regulator or configuration sequence fail",
+	"CPU2 regulator or configuration sequence fail",
+	"CPU3 regulator or configuration sequence fail"
+};
+
+static const char * const CLIPPER_EnvQW3PSIR[] = {
+	"Power Supply 0 is enabled",
+	"Power Supply 1 is enabled",
+	"Power Supply 2 is enabled",
+	"",
+	"Power Supply 0 was enabled but failed",
+	"Power Supply 1 was enabled but failed",
+	"Power Supply 2 was enabled but failed"
+};
+
+static const char * const CLIPPER_EnvQW4LM78ISR[] = {
+	"PS +3.3V out of tolerance",
+	"PS +5V out of tolerance",
+	"PS +12V out of tolerance",
+	"VTERM out of tolerance",
+	"Temperature zone 0 (PCI Backplane slots 1-3 area) over limit failure",
+	"LM75 CPU0-3 Temperature over limit failure",
+	"System Fan 1 failure",
+	"System Fan 2 failure",
+	"CTERM out of tolerance",
+	"",
+	"-12V out of tolerance",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"CPU0_VCORE +2V out of tolerance",
+	"CPU0_VIO +1.5V out of tolerance",
+	"CPU1_VCORE +2V out of tolerance",
+	"CPU1_VIO +1.5V out of tolerance",
+	"Temperature zone 1 (PCI Backplane slots 7-10 area) over limit failure",
+	"",
+	"System Fan 4 failure",
+	"System Fan 5 failure",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"CPU2_VCORE +2V out of tolerance",
+	"CPU2_VIO +1.5V out of tolerance",
+	"CPU3_VCORE +2V out of tolerance",
+	"CPU3_VIO +1.5V out of tolerance",
+	"Temperature zone 2 (PCI Backplane slots 4-6 area) over limit failure",
+	"",
+	"System Fan 3 failure",
+	"System Fan 6 failure",
+	"",
+	"",
+	"Power supply 3.3V rail above high amperage warning",
+	"Power supply 5.0V rail above high amperage warning",
+	"Power supply 12V rail above high amperage warning",
+	"Power supply high temperature warning",
+	"Power supply AC input low limit warning",
+	"Power supply AC input high limit warning"
+};
+
+static const char * const CLIPPER_EnvQW5DOOR[] = {
+	"",
+	"System CPU door is open",
+	"System Fan door is open",
+	"System PCI door is open",
+	"",
+	"System CPU door is closed",
+	"System Fan door is closed",
+	"System PCI door is closed"
+};
+
+static const char * const CLIPPER_EnvQW6TEMP[] = {
+	"CPU0 temperature warning fault has occurred",
+	"CPU1 temperature warning fault has occurred",
+	"CPU2 temperature warning fault has occurred",
+	"CPU3 temperature warning fault has occurred",
+	"System temperature zone 0 warning fault has occurred",
+	"System temperature zone 1 warning fault has occurred",
+	"System temperature zone 2 warning fault has occurred"
+};
+
+static const char * const CLIPPER_EnvQW7FAN[] = {
+	"System Fan 1 is not responding to RMC Commands",
+	"System Fan 2 is not responding to RMC Commands",
+	"System Fan 3 is not responding to RMC Commands",
+	"System Fan 4 is not responding to RMC Commands",
+	"System Fan 5 is not responding to RMC Commands",
+	"System Fan 6 is not responding to RMC Commands",
+	"",
+	"",
+	"CPU fans 5/6 at maximum speed",
+	"CPU fans 5/6 reduced speed from maximum",
+	"PCI fans 1-4 at maximum speed",
+	"PCI fans 1-4 reduced speed from maximum"
+};
+
+#define CLIPPER_ENV_LM78ISR_MASK	0xfcdf00df05ffUL
+
+/* ES40 Service Guide EK-ES240-SV A01, live frame: Tables D-20 and D-21. */
+struct el_clipper_envdata {
+	u64 summary;
+	u64 dir;
+	u64 smir;
+	u64 cpuir;
+	u64 psir;
+	u64 fault;
+	u64 doors;
+	u64 temp_warn;
+	u64 fan_ctrl;
+	u64 fatal_power_down;
+	u64 reserved;
+};
+
+static bool
+clipper_print_bits(const char * const *messages, size_t count,
+		   u64 value, u64 mask)
+{
+	size_t i;
+
+	if (!(value & mask))
+		return false;
+	for (i = 0; i < count; i++)
+		if (value & mask & (1UL << i))
+			printk("%s    %s\n", err_print_prefix, messages[i]);
+	return true;
+}
+
+#define CLIPPER_BITS(table, value, mask) \
+	clipper_print_bits(table, ARRAY_SIZE(table), value, mask)
+
+static void
+clipper_process_environment(struct el_common *header)
+{
+	struct el_clipper_envdata *frame;
+	bool fault = false;
+
+	if (!tsunami_frame_valid(header, sizeof(*frame))) {
+		printk("%s  Truncated Clipper environmental frame\n", err_print_prefix);
+		mchk_dump_logout_frame_raw(header);
+		return;
+	}
+	frame = (void *)header + header->sys_offset;
+	/* Only QW1 through QW7 carry error state in the live 680 frame. */
+	/* PSU summary and inverted halt/reset signals remain raw context. */
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW1SMIR, frame->smir, 0x14);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW2CPUIR, frame->cpuir, 0xf0);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW3PSIR, frame->psir, 0x70);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW4LM78ISR,
+			       frame->fault, CLIPPER_ENV_LM78ISR_MASK);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW5DOOR, frame->doors, 0x0e);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW6TEMP, frame->temp_warn, 0x7f);
+	fault |= CLIPPER_BITS(CLIPPER_EnvQW7FAN, frame->fan_ctrl, 0x3f);
+	/* A notification with no recognized fault can describe recovery. */
+	if (!fault)
+		printk("%s    No recognized environmental fault bits set\n",
+		       err_print_prefix);
+	printk("%s  Environmental summary: %016llx DIR: %016llx\n",
+	       err_print_prefix, frame->summary, frame->dir);
+	printk("%s  SMIR: %016llx (PSU summary/halt/reset bits undecoded)\n",
+	       err_print_prefix, frame->smir);
+	CLIPPER_BITS(CLIPPER_EnvQW2CPUIR, frame->cpuir, 0x0f);
+	CLIPPER_BITS(CLIPPER_EnvQW3PSIR, frame->psir, 0x07);
+	CLIPPER_BITS(CLIPPER_EnvQW5DOOR, frame->doors, 0xe0);
+	CLIPPER_BITS(CLIPPER_EnvQW7FAN, frame->fan_ctrl, 0xf00);
+	if (frame->fault & (0x3fUL << 42))
+		printk("%s  Power supply warning source: %llu (3 = reserved)\n",
+		       err_print_prefix, (frame->fault >> 40) & 3);
+}
+
+void
+clipper_machine_check(unsigned long vector, unsigned long la_ptr)
+{
+	struct el_common *header = (void *)la_ptr;
+	char *saved_err_prefix = err_print_prefix;
+
+	if (vector != SCB_Q_SYSEVENT) {
+		tsunami_machine_check(vector, la_ptr);
+		return;
+	}
+	/* Drain pending accesses before inspecting the environmental frame. */
+	mb();
+	draina();
+	err_print_prefix = KERN_CRIT;
+	printk("%sSystem correctable environmental event (code %x) on CPU %d:\n",
+	       err_print_prefix, header->code, smp_processor_id());
+	if (header->code == 0x206)
+		clipper_process_environment(header);
+	else {
+		printk("%s  Unrecognized environmental event; raw frame follows\n",
+		       err_print_prefix);
+		mchk_dump_logout_frame_raw(header);
+	}
+	err_print_prefix = saved_err_prefix;
+	wrmces(0x7);
+	/* Complete acknowledgment before returning from the event. */
+	mb();
+}
diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h
index f138bd494628..8cdf72f4ab8b 100644
--- a/arch/alpha/kernel/proto.h
+++ b/arch/alpha/kernel/proto.h
@@ -78,6 +78,7 @@ extern struct _alpha_agp_info *titan_agp_info(void);
 extern struct pci_ops tsunami_pci_ops;
 extern void tsunami_init_arch(void);
 extern void tsunami_kill_arch(int);
+extern void clipper_machine_check(unsigned long vector, unsigned long la_ptr);
 extern void tsunami_machine_check(unsigned long vector, unsigned long la_ptr);
 extern void tsunami_pci_tbi(struct pci_controller *, dma_addr_t, dma_addr_t);
 
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 0a2d319bb1c8..0b5687ab45f2 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -627,7 +627,7 @@ struct alpha_machine_vector clipper_mv __initmv = {
 	DO_EV6_MMU,
 	DO_DEFAULT_RTC,
 	DO_TSUNAMI_IO,
-	.machine_check		= tsunami_machine_check,
+	.machine_check		= clipper_machine_check,
 	.max_isa_dma_address	= ALPHA_MAX_ISA_DMA_ADDRESS,
 	.min_io_address		= DEFAULT_IO_BASE,
 	.min_mem_address	= DEFAULT_MEM_BASE,
-- 
2.43.0