| Message ID | 20181012192937.3819951-1-jeremy.linton@arm.com |
|---|---|
| State | New |
| Headers | show |
| Series | None | expand |
On Fri, Oct 12, 2018 at 02:29:37PM -0500, Jeremy Linton wrote: > The BAD_MADT_GICC_ENTRY check is a little too strict because > it rejects MADT entries that don't match the currently known > lengths. We should remove this restriction to avoid problems > if the table length changes. Future code which might depend on > additional fields should be written to validate those fields > before using them, rather than trying to globally check > known MADT version lengths. > > Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> > --- > arch/arm64/include/asm/acpi.h | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h > index 709208dfdc8b..4d0946bd485a 100644 > --- a/arch/arm64/include/asm/acpi.h > +++ b/arch/arm64/include/asm/acpi.h > @@ -22,12 +22,12 @@ > #include <asm/tlbflush.h> > > /* Macros for consistency checks of the GICC subtable of MADT */ > -#define ACPI_MADT_GICC_LENGTH \ > - (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) > +#define ACPI_MADT_GICC_MIN_LENGTH ACPI_OFFSET( \ > + struct acpi_madt_generic_interrupt, efficiency_class) > This makes it 76 always which is fine, just that the first user of efficiency_class should check for the length before accessing it. No user of efficiency_class yet, so I am fine with this change. > #define BAD_MADT_GICC_ENTRY(entry, end) \ > - (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ > - (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) > + (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ > + (unsigned long)(entry) + (entry)->header.length > (end)) > Acked-by: Sudeep Holla <sudeep.holla@arm.com> -- Regards, Sudeep
On Fri, Oct 12, 2018 at 02:29:37PM -0500, Jeremy Linton wrote: > The BAD_MADT_GICC_ENTRY check is a little too strict because > it rejects MADT entries that don't match the currently known > lengths. We should remove this restriction to avoid problems > if the table length changes. Future code which might depend on > additional fields should be written to validate those fields > before using them, rather than trying to globally check > known MADT version lengths. > > Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> > --- > arch/arm64/include/asm/acpi.h | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) Hi Jeremy, I assume there is no [PATCH 1/2] (to make sure I have not missed anything). > diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h > index 709208dfdc8b..4d0946bd485a 100644 > --- a/arch/arm64/include/asm/acpi.h > +++ b/arch/arm64/include/asm/acpi.h > @@ -22,12 +22,12 @@ > #include <asm/tlbflush.h> > > /* Macros for consistency checks of the GICC subtable of MADT */ > -#define ACPI_MADT_GICC_LENGTH \ > - (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) > +#define ACPI_MADT_GICC_MIN_LENGTH ACPI_OFFSET( \ > + struct acpi_madt_generic_interrupt, efficiency_class) I would add a comment explaining why the efficiency_class offset corresponds to the min length, I will do it myself before sending it upstream. I will take this patch and send it to Will/Catalin with ARM64 ACPI material for v4.21. Thanks, Lorenzo > > #define BAD_MADT_GICC_ENTRY(entry, end) \ > - (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ > - (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) > + (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ > + (unsigned long)(entry) + (entry)->header.length > (end)) > > /* Basic configuration for ACPI */ > #ifdef CONFIG_ACPI > -- > 2.14.3 >
On Thu, Nov 01, 2018 at 11:31:36AM +0000, Lorenzo Pieralisi wrote: > On Fri, Oct 12, 2018 at 02:29:37PM -0500, Jeremy Linton wrote: > > The BAD_MADT_GICC_ENTRY check is a little too strict because > > it rejects MADT entries that don't match the currently known > > lengths. We should remove this restriction to avoid problems > > if the table length changes. Future code which might depend on > > additional fields should be written to validate those fields > > before using them, rather than trying to globally check > > known MADT version lengths. > > > > Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> > > --- > > arch/arm64/include/asm/acpi.h | 8 ++++---- > > 1 file changed, 4 insertions(+), 4 deletions(-) > > Hi Jeremy, > > I assume there is no [PATCH 1/2] (to make sure I have not missed > anything). > IIRC, it's a patch fixing module device table entry for SPE. They are independent, just happened to be put out together. -- Regards, Sudeep
On Fri, Oct 12, 2018 at 02:29:37PM -0500, Jeremy Linton wrote: > The BAD_MADT_GICC_ENTRY check is a little too strict because > it rejects MADT entries that don't match the currently known > lengths. We should remove this restriction to avoid problems > if the table length changes. Future code which might depend on > additional fields should be written to validate those fields > before using them, rather than trying to globally check > known MADT version lengths. > > Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> > --- > arch/arm64/include/asm/acpi.h | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) Hi Jeremy, as mentioned, I added a comment to the macro so that in the future we will be able to remember the logic behind it. I pushed the commit out: git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/linux.git acpi/madt Please have a look, if I hear no objections I shall be sending it to Will and Catalin to queue it for v4.21. Thanks, Lorenzo > diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h > index 709208dfdc8b..4d0946bd485a 100644 > --- a/arch/arm64/include/asm/acpi.h > +++ b/arch/arm64/include/asm/acpi.h > @@ -22,12 +22,12 @@ > #include <asm/tlbflush.h> > > /* Macros for consistency checks of the GICC subtable of MADT */ > -#define ACPI_MADT_GICC_LENGTH \ > - (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) > +#define ACPI_MADT_GICC_MIN_LENGTH ACPI_OFFSET( \ > + struct acpi_madt_generic_interrupt, efficiency_class) > > #define BAD_MADT_GICC_ENTRY(entry, end) \ > - (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ > - (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) > + (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ > + (unsigned long)(entry) + (entry)->header.length > (end)) > > /* Basic configuration for ACPI */ > #ifdef CONFIG_ACPI > -- > 2.14.3 >
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 709208dfdc8b..4d0946bd485a 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -22,12 +22,12 @@ #include <asm/tlbflush.h> /* Macros for consistency checks of the GICC subtable of MADT */ -#define ACPI_MADT_GICC_LENGTH \ - (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) +#define ACPI_MADT_GICC_MIN_LENGTH ACPI_OFFSET( \ + struct acpi_madt_generic_interrupt, efficiency_class) #define BAD_MADT_GICC_ENTRY(entry, end) \ - (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ - (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) + (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ + (unsigned long)(entry) + (entry)->header.length > (end)) /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI
The BAD_MADT_GICC_ENTRY check is a little too strict because it rejects MADT entries that don't match the currently known lengths. We should remove this restriction to avoid problems if the table length changes. Future code which might depend on additional fields should be written to validate those fields before using them, rather than trying to globally check known MADT version lengths. Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> --- arch/arm64/include/asm/acpi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) -- 2.14.3