| Message ID | 20181226033450.5098-1-fanc.fnst@cn.fujitsu.com (mailing list archive) |
|---|---|
| State | Accepted, archived |
| Delegated to: | Rafael Wysocki |
| Headers | show |
| Series | ACPI: Change wrong print type to display the real value for i386-PAE | expand |
On Wednesday, December 26, 2018 4:34:50 AM CET Chao Fan wrote: > There is a wrong display for memory address of NUMA node in i386-PAE. > That may mislead developers. > > Here is a debian9-32bit with PAE in QEMU guest whose total memory is > more than 4G: > qemu-system-i386 \ > -hda /var/lib/libvirt/images/debian32.qcow2 \ > -m 5G \ > -enable-kvm \ > -smp 10 \ > -numa node,mem=512M,nodeid=0,cpus=0 \ > -numa node,mem=512M,nodeid=1,cpus=1 \ > -numa node,mem=512M,nodeid=2,cpus=2 \ > -numa node,mem=512M,nodeid=3,cpus=3 \ > -numa node,mem=512M,nodeid=4,cpus=4 \ > -numa node,mem=512M,nodeid=5,cpus=5 \ > -numa node,mem=512M,nodeid=6,cpus=6 \ > -numa node,mem=512M,nodeid=7,cpus=7 \ > -numa node,mem=512M,nodeid=8,cpus=8 \ > -numa node,mem=512M,nodeid=9,cpus=9 \ > -serial stdio > > Because of the wrong value type, it prints as below: > [ 0.021049] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled > [ 0.021740] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled > [ 0.022425] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled > [ 0.023092] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled > [ 0.023764] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled > [ 0.024431] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled > [ 0.025104] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled > [ 0.025791] ACPI: SRAT Memory (0x0 length 0x20000000) in proximity domain 6 enabled > [ 0.026412] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 7 enabled > [ 0.027118] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 8 enabled > [ 0.027802] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 9 enabled > The upper half of start address from domain 6 to domain 9 was cut so > that developers get a wrong value. > > Fix the value type, it prints as below: > [ 0.023698] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled > [ 0.024325] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled > [ 0.024981] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled > [ 0.025659] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled > [ 0.026317] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled > [ 0.026980] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled > [ 0.027635] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled > [ 0.028311] ACPI: SRAT Memory (0x100000000 length 0x20000000) in proximity domain 6 enabled > [ 0.028985] ACPI: SRAT Memory (0x120000000 length 0x20000000) in proximity domain 7 enabled > [ 0.029667] ACPI: SRAT Memory (0x140000000 length 0x20000000) in proximity domain 8 enabled > [ 0.030334] ACPI: SRAT Memory (0x160000000 length 0x20000000) in proximity domain 9 enabled > The start address from domain 6 to domain 9 is the real value. > > Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> > --- > drivers/acpi/numa.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c > index 274699463b4f..7bbbf8256a41 100644 > --- a/drivers/acpi/numa.c > +++ b/drivers/acpi/numa.c > @@ -146,9 +146,9 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) > { > struct acpi_srat_mem_affinity *p = > (struct acpi_srat_mem_affinity *)header; > - pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n", > - (unsigned long)p->base_address, > - (unsigned long)p->length, > + pr_debug("SRAT Memory (0x%llx length 0x%llx) in proximity domain %d %s%s%s\n", > + (unsigned long long)p->base_address, > + (unsigned long long)p->length, > p->proximity_domain, > (p->flags & ACPI_SRAT_MEM_ENABLED) ? > "enabled" : "disabled", > Applied, thanks!
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 274699463b4f..7bbbf8256a41 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -146,9 +146,9 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) { struct acpi_srat_mem_affinity *p = (struct acpi_srat_mem_affinity *)header; - pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n", - (unsigned long)p->base_address, - (unsigned long)p->length, + pr_debug("SRAT Memory (0x%llx length 0x%llx) in proximity domain %d %s%s%s\n", + (unsigned long long)p->base_address, + (unsigned long long)p->length, p->proximity_domain, (p->flags & ACPI_SRAT_MEM_ENABLED) ? "enabled" : "disabled",
There is a wrong display for memory address of NUMA node in i386-PAE. That may mislead developers. Here is a debian9-32bit with PAE in QEMU guest whose total memory is more than 4G: qemu-system-i386 \ -hda /var/lib/libvirt/images/debian32.qcow2 \ -m 5G \ -enable-kvm \ -smp 10 \ -numa node,mem=512M,nodeid=0,cpus=0 \ -numa node,mem=512M,nodeid=1,cpus=1 \ -numa node,mem=512M,nodeid=2,cpus=2 \ -numa node,mem=512M,nodeid=3,cpus=3 \ -numa node,mem=512M,nodeid=4,cpus=4 \ -numa node,mem=512M,nodeid=5,cpus=5 \ -numa node,mem=512M,nodeid=6,cpus=6 \ -numa node,mem=512M,nodeid=7,cpus=7 \ -numa node,mem=512M,nodeid=8,cpus=8 \ -numa node,mem=512M,nodeid=9,cpus=9 \ -serial stdio Because of the wrong value type, it prints as below: [ 0.021049] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled [ 0.021740] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled [ 0.022425] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled [ 0.023092] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled [ 0.023764] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled [ 0.024431] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled [ 0.025104] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled [ 0.025791] ACPI: SRAT Memory (0x0 length 0x20000000) in proximity domain 6 enabled [ 0.026412] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 7 enabled [ 0.027118] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 8 enabled [ 0.027802] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 9 enabled The upper half of start address from domain 6 to domain 9 was cut so that developers get a wrong value. Fix the value type, it prints as below: [ 0.023698] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled [ 0.024325] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled [ 0.024981] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled [ 0.025659] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled [ 0.026317] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled [ 0.026980] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled [ 0.027635] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled [ 0.028311] ACPI: SRAT Memory (0x100000000 length 0x20000000) in proximity domain 6 enabled [ 0.028985] ACPI: SRAT Memory (0x120000000 length 0x20000000) in proximity domain 7 enabled [ 0.029667] ACPI: SRAT Memory (0x140000000 length 0x20000000) in proximity domain 8 enabled [ 0.030334] ACPI: SRAT Memory (0x160000000 length 0x20000000) in proximity domain 9 enabled The start address from domain 6 to domain 9 is the real value. Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> --- drivers/acpi/numa.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)