linux.git/arch/x86/kernel/cpu/resctrl/internal.h, branch v6.0

x86/resctrl: Merge the CDP resources

2021-08-11T16:39:42+00:00

resctrl uses struct rdt_resource to describe the available hardware
resources. The domains of the CDP aliases share a single ctrl_val[]
array. The only differences between the struct rdt_hw_resource aliases
is the name and conf_type.

The name from struct rdt_hw_resource is visible to user-space. To
support another architecture, as many user-visible details should be
handled in the filesystem parts of the code that is common to all
architectures. The name and conf_type go together.

Remove conf_type and the CDP aliases. When CDP is supported and enabled,
schemata_list_create() can create two schemata using the single
resource, generating the CODE/DATA suffix to the schema name itself.

This allows the alloc_ctrlval_array() and complications around free()ing
the ctrl_val arrays to be removed.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-25-james.morse@arm.com

x86/resctrl: Apply offset correction when config is staged

2021-08-11T16:03:28+00:00

When resctrl comes to copy the CAT MSR values from the ctrl_val[] array
into hardware, it applies an offset adjustment based on the type of
the resource. CODE and DATA resources have their closid mapped into an
odd/even range. This mapping is based on a property of the resource.

This happens once the new control value has been written to the ctrl_val[]
array. Once the CDP resources are merged, there will only be a single
property that needs to cover both odd/even mappings to the single
ctrl_val[] array. The offset adjustment must be applied before the new
value is written to the array.

Move the logic from cat_wrmsr() to resctrl_arch_update_domains(). The
value provided to apply_config() is now an index in the array, not the
closid. The parameters provided via struct msr_param are now indexes
too. As resctrl's use of closid is a u32, struct msr_param's type is
changed to match.

With this, the CODE and DATA resources only use the odd or even
indexes in the array. This allows the temporary num_closid/2 fixes in
domain_setup_ctrlval() and reset_all_ctrls() to be removed.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-20-james.morse@arm.com

x86/resctrl: Rename update_domains() to resctrl_arch_update_domains()

2021-08-11T14:36:58+00:00

update_domains() merges the staged configuration changes into the arch
codes configuration array. Rename to make it clear it is part of the
arch code interface to resctrl.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-16-james.morse@arm.com

x86/resctrl: Add a helper to read/set the CDP configuration

2021-08-11T13:54:26+00:00

Whether CDP is enabled for a hardware resource like the L3 cache can be
found by inspecting the alloc_enabled flags of the L3CODE/L3DATA struct
rdt_hw_resources, even if they aren't in use.

Once these resources are merged, the flags can't be compared. Whether
CDP is enabled needs tracking explicitly. If another architecture is
emulating CDP the behaviour may not be per-resource. 'cdp_capable' needs
to be visible to resctrl, even if its not in use, as this affects the
padding of the schemata table visible to user-space.

Add cdp_enabled to struct rdt_hw_resource and cdp_capable to struct
rdt_resource. Add resctrl_arch_set_cdp_enabled() to let resctrl enable
or disable CDP on a resource. resctrl_arch_get_cdp_enabled() lets it
read the current state.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-12-james.morse@arm.com

x86/resctrl: Swizzle rdt_resource and resctrl_schema in pseudo_lock_region

2021-08-11T13:51:45+00:00

struct pseudo_lock_region points to the rdt_resource.

Once the resources are merged, this won't be unique. The resource name
is moving into the schema, so that the filesystem portions of resctrl can
generate it.

Swap pseudo_lock_region's rdt_resource pointer for a schema pointer.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-11-james.morse@arm.com

x86/resctrl: Pass the schema to resctrl filesystem functions

2021-08-11T13:43:54+00:00

Once the CDP resources are merged, there will be two struct
resctrl_schema for one struct rdt_resource. CDP becomes a type of
configuration that belongs to the schema.

Helpers like rdtgroup_cbm_overlaps() need access to the schema to query
the configuration (or configurations) based on schema properties.

Change these functions to take a struct schema instead of the struct
rdt_resource. All the modified functions are part of the filesystem code
that will move to /fs/resctrl once it is possible to support a second
architecture.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-10-james.morse@arm.com

x86/resctrl: Add resctrl_arch_get_num_closid()

2021-08-11T13:35:42+00:00

To initialise struct resctrl_schema's num_closid, schemata_list_create()
reaches into the architectures private structure to retrieve num_closid
from the struct rdt_hw_resource. The 'half the closids' behaviour should
be part of the filesystem parts of resctrl that are the same on any
architecture. struct resctrl_schema's num_closid should include any
correction for CDP.

Having two properties called num_closid is likely to be confusing when
they have different values.

Add a helper to read the resource's num_closid from the arch code.
This should return the number of closid that the resource supports,
regardless of whether CDP is in use. Once the CDP resources are merged,
schemata_list_create() can apply the correction itself.

Using a type with an obvious size for the arch helper means changing the
type of num_closid to u32, which matches the type already used by struct
rdtgroup.

reset_all_ctrls() does not use resctrl_arch_get_num_closid(), even
though it sets up a structure for modifying the hardware. This function
will be part of the architecture code, the maximum closid should be the
maximum value the hardware has, regardless of the way resctrl is using
it. All the uses of num_closid in core.c are naturally part of the
architecture specific code.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-9-james.morse@arm.com

x86/resctrl: Label the resources with their configuration type

2021-08-11T11:13:18+00:00

The names of resources are used for the schema name presented to
user-space. The name used is rooted in a structure provided by the
architecture code because the names are different when CDP is enabled.
x86 implements this by swapping between two sets of resource structures
based on their alloc_enabled flag. The type of configuration in-use is
encoded in the name (and cbm_idx_offset).

Once the CDP behaviour is moved into the parts of resctrl that will
move to /fs/, there will be two struct resctrl_schema for one struct
rdt_resource. The schema describes the type of configuration being
applied to the resource. The name of the schema should be generated
by resctrl, base on the type of configuration. To do this struct
resctrl_schema needs to store the type of configuration in use for a
schema.

Create an enum resctrl_conf_type describing the options, and add it to
struct resctrl_schema. The underlying resources are still separate, as
cbm_idx_offset is still in use.

Temporarily label all the entries in rdt_resources_all[] and copy that
value to struct resctrl_schema. Copying the value ensures there is no
mismatch while the filesystem parts of resctrl are modified to use the
schema. Once the resources are merged, the filesystem code can assign
this value based on the schema being created.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-6-james.morse@arm.com

x86/resctrl: Add a separate schema list for resctrl

2021-08-11T10:28:01+00:00

Resctrl exposes schemata to user-space, which allow the control values
to be specified for a group of tasks.

User-visible properties of the interface, (such as the schemata names
and how the values are parsed) are rooted in a struct provided by the
architecture code. (struct rdt_hw_resource). Once a second architecture
uses resctrl, this would allow user-visible properties to diverge
between architectures.

These properties should come from the resctrl code that will be common
to all architectures. Resctrl has no per-schema structure, only struct
rdt_{hw_,}resource. Create a struct resctrl_schema to hold the
rdt_resource. Before a second architecture can be supported, this
structure will also need to hold the schema name visible to user-space
and the type of configuration values for resctrl.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-4-james.morse@arm.com

x86/resctrl: Split struct rdt_domain

2021-08-11T10:00:43+00:00

resctrl is the defacto Linux ABI for SoC resource partitioning features.

To support it on another architecture, it needs to be abstracted from
the features provided by Intel RDT and AMD PQoS, and moved to /fs/.
struct rdt_domain contains a mix of architecture private details and
properties of the filesystem interface user-space uses.

Continue by splitting struct rdt_domain, into an architecture private
'hw' struct, which contains the common resctrl structure that would be
used by any architecture. The hardware values in ctrl_val and mbps_val
need to be accessed via helpers to allow another architecture to convert
these into a different format if necessary. After this split, filesystem
code paths touching a 'hw' struct indicates where an abstraction is
needed.

Splitting this structure only moves types around, and should not lead
to any change in behaviour.

Signed-off-by: James Morse 
Signed-off-by: Borislav Petkov 
Reviewed-by: Jamie Iles 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lkml.kernel.org/r/20210728170637.25610-3-james.morse@arm.com