Now return AE_BAD_PARAMETER if the input register pointer is null,
and AE_BAD_ADDRESS if the register has an address of zero.
Previously, these cases simply returned AE_OK. For optional registers
such as PM1B status/enable/control, the caller should check for a valid
register address before calling.
ACPICA BZ 748.
The PM1B registers are mirrors of the PM1A registers with different
bits actually implemented. From the ACPI specification:
"Although the bits can be split between the two register blocks (each
register block has a unique pointer within the FADT), the bit positions
are maintained. The register block with unimplemented bits (that is, those
implemented in the other register block) always returns zeros, and
writes have no side effects"
This function was writing an optional PM1B status register twice.
The existing call to the low-level AcpiHwRegisterWrite automatically
handles a possibly split PM1 A/B register.
ACPICA BZ 751.
On read, shift B register bits above the A bits. On write, shift B bits
down to zero before writing the B register. New: AcpiHwReadMultiple,
AcpiHwWriteMultiple. These two functions now transparently handle the
(possible) split registers for PM1 Status, Enable, and Control.
Add new globals for the PM1 status registers (A/B), similar to the
way the PM1 enable registers are handled. Instead of overloading the
FADT Event Register blocks. This makes the code clearer and less prone
to error.
Add 2009 copyright to all module headers and signons, including the Linux
header. This affects virtually every file in the ACPICA core subsystem,
iASL compiler, and all utilities.
1) Decode all Boot Architecture flags.
2) Decode all flags, regardless of the FADT version. Previously,
only those flags that were actually valid for the FADT version
were displayed. This seemed to omit some information.
Previously, the table override mechanism was implemented for the
DSDT only. Now, any table in the RSDT/XSDT can be replaced by the
host OS. (including the DSDT).
This returns the FADT support to the original behavior, which is to
use default register widths. However, now check each register
definition and report a warning if it differs from the default.
This is a first step to moving away from the default widths, rather
than outright believing the widths in all FADTs for all machines,
considered rather dangerous until more data is obtained.
1) Update the register lengths for the PM1 event blocks. The length
must be divided by two in order to use these to access the status
registers.
2) Add run-time option to use default register lengths to override a
faulty FADT.
3) Add warning message if any of the X64 address structures contain a
length that does not match the legacy length earlier in the FADT.
4) Move all FADT warning messages into the ValidateFadt function.
1) Clear external list generated by Scope in external tables
2) Set node owner id only if it satisfies all the following conditions
a. Not a predefined node, _SB_ etc.
b. Not the root node
c. Not a node created by Scope
3) Precise object types for External statements, for example
- External (\_PR_.CPU0, DeviceObj)
+ External (\_PR_.CPU0, ProcessorObj)
Uses the FADT-defined reset register and reset value. Checks the
FADT flags for the reset register supported bit. Supports reset
register in memory or I/O space, but not in PCI config space since
the host has the information to do it.
Changed the HwLowLevelRead and HwLowLevelWrite functions to the public
AcpiRead and AcpiWrite to allow direct access to ACPI registers.
Removed the "width" parameter since the width can be obtained from the
input GAS structure. Updated the FADT initialization to setup the GAS
structures with the proper widths. Some widths are still hardcoded
because many FADTs have incorrect register lengths.
This function maps an input GPE index to a GPE block device. Also
Added AcpiCurrentGpeCount to track the current number of GPEs that
are being managed by the ACPICA core (both FADT-based GPEs and the GPEs
contained in GPE block devices.)
Previously did not allow the creation of named objects within a while
loop. However, it is not possible to analyze the loop to determine if
a named object would actually be created twice. Also, compiling
disassembled code with switch statements would raise this error even
though the compiler-emitted while(one) loop only executed once (there
is a break statement at the bottom of the loop. Chalk this one up to
'a nice try'.
For Windows compatibility, return an implicit integer of value
zero for methods that have no executable code. A default implicit
value of zero is provided for methods.
Such methods are seen in the field as stubs (presumably), and can
cause drivers to fail if they expect a return value. Lin Ming.
Merge the code that validates control method argument counts into
the predefined validation module. Eliminates possible multiple
warnings for incorrect counts.
This can happen if the _WAK method returns nothing (as per ACPI 1.0)
but does return an integer if the implicit return mechanism is enabled.
This is the only method that has this problem, since it is also
defined to return a package of two integers (ACPI 1.0b+). In all
other cases, if a method returns an object when one was not expected,
no warning is issued.
