android_kernel_sony_sdm845/arch/x86/kernel/apic/x2apic_phys.c

152 lines
3.8 KiB
C
Raw Normal View History

#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/dmar.h>
#include <asm/smp.h>
#include <asm/x2apic.h>
int x2apic_phys;
static struct apic apic_x2apic_phys;
static int set_x2apic_phys_mode(char *arg)
{
x2apic_phys = 1;
return 0;
}
early_param("x2apic_phys", set_x2apic_phys_mode);
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 <song-bo.wang@hp.com> [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-07 10:53:02 -08:00
static bool x2apic_fadt_phys(void)
{
#ifdef CONFIG_ACPI
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 <song-bo.wang@hp.com> [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-07 10:53:02 -08:00
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 true;
}
#endif
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 <song-bo.wang@hp.com> [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-07 10:53:02 -08:00
return false;
}
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
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 <song-bo.wang@hp.com> [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-07 10:53:02 -08:00
return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
}
static void x2apic_send_IPI(int cpu, int vector)
{
u32 dest = per_cpu(x86_cpu_to_apicid, cpu);
x86/apic: Add extra serialization for non-serializing MSRs commit 25a068b8e9a4eb193d755d58efcb3c98928636e0 upstream. Jan Kiszka reported that the x2apic_wrmsr_fence() function uses a plain MFENCE while the Intel SDM (10.12.3 MSR Access in x2APIC Mode) calls for MFENCE; LFENCE. Short summary: we have special MSRs that have weaker ordering than all the rest. Add fencing consistent with current SDM recommendations. This is not known to cause any issues in practice, only in theory. Longer story below: The reason the kernel uses a different semantic is that the SDM changed (roughly in late 2017). The SDM changed because folks at Intel were auditing all of the recommended fences in the SDM and realized that the x2apic fences were insufficient. Why was the pain MFENCE judged insufficient? WRMSR itself is normally a serializing instruction. No fences are needed because the instruction itself serializes everything. But, there are explicit exceptions for this serializing behavior written into the WRMSR instruction documentation for two classes of MSRs: IA32_TSC_DEADLINE and the X2APIC MSRs. Back to x2apic: WRMSR is *not* serializing in this specific case. But why is MFENCE insufficient? MFENCE makes writes visible, but only affects load/store instructions. WRMSR is unfortunately not a load/store instruction and is unaffected by MFENCE. This means that a non-serializing WRMSR could be reordered by the CPU to execute before the writes made visible by the MFENCE have even occurred in the first place. This means that an x2apic IPI could theoretically be triggered before there is any (visible) data to process. Does this affect anything in practice? I honestly don't know. It seems quite possible that by the time an interrupt gets to consume the (not yet) MFENCE'd data, it has become visible, mostly by accident. To be safe, add the SDM-recommended fences for all x2apic WRMSRs. This also leaves open the question of the _other_ weakly-ordered WRMSR: MSR_IA32_TSC_DEADLINE. While it has the same ordering architecture as the x2APIC MSRs, it seems substantially less likely to be a problem in practice. While writes to the in-memory Local Vector Table (LVT) might theoretically be reordered with respect to a weakly-ordered WRMSR like TSC_DEADLINE, the SDM has this to say: In x2APIC mode, the WRMSR instruction is used to write to the LVT entry. The processor ensures the ordering of this write and any subsequent WRMSR to the deadline; no fencing is required. But, that might still leave xAPIC exposed. The safest thing to do for now is to add the extra, recommended LFENCE. [ bp: Massage commit message, fix typos, drop accidentally added newline to tools/arch/x86/include/asm/barrier.h. ] Reported-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Link: https://lkml.kernel.org/r/20200305174708.F77040DD@viggo.jf.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-03-05 09:47:08 -08:00
/* x2apic MSRs are special and need a special fence: */
weak_wrmsr_fence();
__x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL);
}
static void
__x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
{
unsigned long query_cpu;
unsigned long this_cpu;
unsigned long flags;
x86/apic: Add extra serialization for non-serializing MSRs commit 25a068b8e9a4eb193d755d58efcb3c98928636e0 upstream. Jan Kiszka reported that the x2apic_wrmsr_fence() function uses a plain MFENCE while the Intel SDM (10.12.3 MSR Access in x2APIC Mode) calls for MFENCE; LFENCE. Short summary: we have special MSRs that have weaker ordering than all the rest. Add fencing consistent with current SDM recommendations. This is not known to cause any issues in practice, only in theory. Longer story below: The reason the kernel uses a different semantic is that the SDM changed (roughly in late 2017). The SDM changed because folks at Intel were auditing all of the recommended fences in the SDM and realized that the x2apic fences were insufficient. Why was the pain MFENCE judged insufficient? WRMSR itself is normally a serializing instruction. No fences are needed because the instruction itself serializes everything. But, there are explicit exceptions for this serializing behavior written into the WRMSR instruction documentation for two classes of MSRs: IA32_TSC_DEADLINE and the X2APIC MSRs. Back to x2apic: WRMSR is *not* serializing in this specific case. But why is MFENCE insufficient? MFENCE makes writes visible, but only affects load/store instructions. WRMSR is unfortunately not a load/store instruction and is unaffected by MFENCE. This means that a non-serializing WRMSR could be reordered by the CPU to execute before the writes made visible by the MFENCE have even occurred in the first place. This means that an x2apic IPI could theoretically be triggered before there is any (visible) data to process. Does this affect anything in practice? I honestly don't know. It seems quite possible that by the time an interrupt gets to consume the (not yet) MFENCE'd data, it has become visible, mostly by accident. To be safe, add the SDM-recommended fences for all x2apic WRMSRs. This also leaves open the question of the _other_ weakly-ordered WRMSR: MSR_IA32_TSC_DEADLINE. While it has the same ordering architecture as the x2APIC MSRs, it seems substantially less likely to be a problem in practice. While writes to the in-memory Local Vector Table (LVT) might theoretically be reordered with respect to a weakly-ordered WRMSR like TSC_DEADLINE, the SDM has this to say: In x2APIC mode, the WRMSR instruction is used to write to the LVT entry. The processor ensures the ordering of this write and any subsequent WRMSR to the deadline; no fencing is required. But, that might still leave xAPIC exposed. The safest thing to do for now is to add the extra, recommended LFENCE. [ bp: Massage commit message, fix typos, drop accidentally added newline to tools/arch/x86/include/asm/barrier.h. ] Reported-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Link: https://lkml.kernel.org/r/20200305174708.F77040DD@viggo.jf.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-03-05 09:47:08 -08:00
/* x2apic MSRs are special and need a special fence: */
weak_wrmsr_fence();
local_irq_save(flags);
this_cpu = smp_processor_id();
for_each_cpu(query_cpu, mask) {
if (apic_dest == APIC_DEST_ALLBUT && this_cpu == query_cpu)
continue;
__x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
vector, APIC_DEST_PHYSICAL);
}
local_irq_restore(flags);
}
static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
{
__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLINC);
}
static void
x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_allbutself(int vector)
{
__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_all(int vector)
{
__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
}
static void init_x2apic_ldr(void)
{
}
static int x2apic_phys_probe(void)
{
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 <song-bo.wang@hp.com> [ updated the changelog and simplified the code ] Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1360263182-16226-1-git-send-email-yinghai@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-07 10:53:02 -08:00
if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
return 1;
return apic == &apic_x2apic_phys;
}
static struct apic apic_x2apic_phys __ro_after_init = {
.name = "physical x2apic",
.probe = x2apic_phys_probe,
.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
.apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
.irq_delivery_mode = dest_Fixed,
.irq_dest_mode = 0, /* physical */
.target_cpus = online_target_cpus,
.disable_esr = 0,
.dest_logical = 0,
.check_apicid_used = NULL,
.vector_allocation_domain = default_vector_allocation_domain,
.init_apic_ldr = init_x2apic_ldr,
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.check_phys_apicid_present = default_check_phys_apicid_present,
.phys_pkg_id = x2apic_phys_pkg_id,
.get_apic_id = x2apic_get_apic_id,
.set_apic_id = x2apic_set_apic_id,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
.send_IPI = x2apic_send_IPI,
.send_IPI_mask = x2apic_send_IPI_mask,
.send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
.send_IPI_all = x2apic_send_IPI_all,
.send_IPI_self = x2apic_send_IPI_self,
.inquire_remote_apic = NULL,
.read = native_apic_msr_read,
.write = native_apic_msr_write,
.eoi_write = native_apic_msr_eoi_write,
.icr_read = native_x2apic_icr_read,
.icr_write = native_x2apic_icr_write,
.wait_icr_idle = native_x2apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
};
apic_driver(apic_x2apic_phys);