leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1f106ff0ea
linux/drivers/iommu
History
Parav Pandit 1f106ff0ea iommu/vt-d: Use bitfields for DMAR capabilities 
IOTLB device presence, iommu coherency and snooping are boolean
capabilities. Use them as bits and keep them adjacent.

Structure layout before the reorg.
$ pahole -C dmar_domain drivers/iommu/intel/dmar.o
struct dmar_domain {
        int                        nid;                  /*     0     4 */
        unsigned int               iommu_refcnt[128];    /*     4   512 */
        /* --- cacheline 8 boundary (512 bytes) was 4 bytes ago --- */
        u16                        iommu_did[128];       /*   516   256 */
        /* --- cacheline 12 boundary (768 bytes) was 4 bytes ago --- */
        bool                       has_iotlb_device;     /*   772     1 */

        /* XXX 3 bytes hole, try to pack */

        struct list_head           devices;              /*   776    16 */
        struct list_head           subdevices;           /*   792    16 */
        struct iova_domain         iovad __attribute__((__aligned__(8)));
							 /*   808  2320 */
        /* --- cacheline 48 boundary (3072 bytes) was 56 bytes ago --- */
        struct dma_pte *           pgd;                  /*  3128     8 */
        /* --- cacheline 49 boundary (3136 bytes) --- */
        int                        gaw;                  /*  3136     4 */
        int                        agaw;                 /*  3140     4 */
        int                        flags;                /*  3144     4 */
        int                        iommu_coherency;      /*  3148     4 */
        int                        iommu_snooping;       /*  3152     4 */
        int                        iommu_count;          /*  3156     4 */
        int                        iommu_superpage;      /*  3160     4 */

        /* XXX 4 bytes hole, try to pack */

        u64                        max_addr;             /*  3168     8 */
        u32                        default_pasid;        /*  3176     4 */

        /* XXX 4 bytes hole, try to pack */

        struct iommu_domain        domain;               /*  3184    72 */

        /* size: 3256, cachelines: 51, members: 18 */
        /* sum members: 3245, holes: 3, sum holes: 11 */
        /* forced alignments: 1 */
        /* last cacheline: 56 bytes */
} __attribute__((__aligned__(8)));

After arranging it for natural padding and to make flags as u8 bits, it
saves 8 bytes for the struct.

struct dmar_domain {
        int                        nid;                  /*     0     4 */
        unsigned int               iommu_refcnt[128];    /*     4   512 */
        /* --- cacheline 8 boundary (512 bytes) was 4 bytes ago --- */
        u16                        iommu_did[128];       /*   516   256 */
        /* --- cacheline 12 boundary (768 bytes) was 4 bytes ago --- */
        u8                         has_iotlb_device:1;   /*   772: 0  1 */
        u8                         iommu_coherency:1;    /*   772: 1  1 */
        u8                         iommu_snooping:1;     /*   772: 2  1 */

        /* XXX 5 bits hole, try to pack */
        /* XXX 3 bytes hole, try to pack */

        struct list_head           devices;              /*   776    16 */
        struct list_head           subdevices;           /*   792    16 */
        struct iova_domain         iovad __attribute__((__aligned__(8)));
							 /*   808  2320 */
        /* --- cacheline 48 boundary (3072 bytes) was 56 bytes ago --- */
        struct dma_pte *           pgd;                  /*  3128     8 */
        /* --- cacheline 49 boundary (3136 bytes) --- */
        int                        gaw;                  /*  3136     4 */
        int                        agaw;                 /*  3140     4 */
        int                        flags;                /*  3144     4 */
        int                        iommu_count;          /*  3148     4 */
        int                        iommu_superpage;      /*  3152     4 */

        /* XXX 4 bytes hole, try to pack */

        u64                        max_addr;             /*  3160     8 */
        u32                        default_pasid;        /*  3168     4 */

        /* XXX 4 bytes hole, try to pack */

        struct iommu_domain        domain;               /*  3176    72 */

        /* size: 3248, cachelines: 51, members: 18 */
        /* sum members: 3236, holes: 3, sum holes: 11 */
        /* sum bitfield members: 3 bits, bit holes: 1, sum bit holes: 5 bits */
        /* forced alignments: 1 */
        /* last cacheline: 48 bytes */
} __attribute__((__aligned__(8)));

Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210530075053.264218-1-parav@nvidia.com
Link: https://lore.kernel.org/r/20210610020115.1637656-20-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
2021-06-10 09:06:13 +02:00
..
amd iommu/amd: Fix wrong parentheses on page-specific invalidations 2021-05-18 11:21:28 +02:00
arm iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
intel iommu/vt-d: Use bitfields for DMAR capabilities 2021-06-10 09:06:13 +02:00
dma-iommu.c Merge branch 'stable/for-linus-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb 2021-05-04 10:58:49 -07:00
exynos-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
fsl_pamu_domain.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
fsl_pamu_domain.h iommu/fsl_pamu: remove the snoop_id field 2021-04-07 10:56:52 +02:00
fsl_pamu.c iommu/fsl_pamu: hardcode the window address and size in pamu_config_ppaace 2021-04-07 10:56:52 +02:00
fsl_pamu.h iommu/fsl_pamu: hardcode the window address and size in pamu_config_ppaace 2021-04-07 10:56:52 +02:00
hyperv-iommu.c iommu/hyperv: setup an IO-APIC IRQ remapping domain for root partition 2021-02-11 08:47:07 +00:00
io-pgfault.c iommu: Add a page fault handler 2021-04-07 10:54:29 +02:00
io-pgtable-arm-v7s.c iommu/io-pgtable-arm-v7s: Quad lvl1 pgtable for MediaTek 2021-02-01 11:31:17 +00:00
io-pgtable-arm.c IOMMU updates for 5.11 2020-12-16 13:58:47 -08:00
io-pgtable-arm.h iommu/io-pgtable-arm: Move some definitions to a header 2020-09-28 23:48:06 +01:00
io-pgtable.c iommu/amd: Prepare for generic IO page table framework 2021-01-28 16:51:17 +01:00
ioasid.c iommu/ioasid: Add ioasid references 2020-11-23 14:16:55 +00:00
iommu-debugfs.c
iommu-sva-lib.c iommu/sva: Add PASID helpers 2020-11-23 14:16:55 +00:00
iommu-sva-lib.h iommu: Add a page fault handler 2021-04-07 10:54:29 +02:00
iommu-sysfs.c drivers/iommu: Export core IOMMU API symbols to permit modular drivers 2019-12-23 14:06:05 +01:00
iommu-traces.c
iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
iova.c iommu: Stop exporting free_iova_fast() 2021-04-07 10:30:48 +02:00
ipmmu-vmsa.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
irq_remapping.c x86: Kill all traces of irq_remapping_get_irq_domain() 2020-10-28 20:26:28 +01:00
irq_remapping.h x86: Kill all traces of irq_remapping_get_irq_domain() 2020-10-28 20:26:28 +01:00
Kconfig Merge branches 'iommu/fixes', 'arm/mediatek', 'arm/smmu', 'arm/exynos', 'unisoc', 'x86/vt-d', 'x86/amd' and 'core' into next 2021-04-16 17:16:03 +02:00
Makefile Merge branches 'iommu/fixes', 'arm/mediatek', 'arm/smmu', 'arm/exynos', 'unisoc', 'x86/vt-d', 'x86/amd' and 'core' into next 2021-04-16 17:16:03 +02:00
msm_iommu_hw-8xxx.h
msm_iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
msm_iommu.h
mtk_iommu_v1.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
mtk_iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
mtk_iommu.h iommu/mediatek: Add mt8192 support 2021-02-01 11:31:19 +00:00
of_iommu.c iommu/arm-smmu-v3: Use device properties for pasid-num-bits 2021-04-07 10:54:28 +02:00
omap-iommu-debug.c iommu/omap: Check for failure of a call to omap_iommu_dump_ctx 2020-07-22 15:02:33 +02:00
omap-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
omap-iommu.h iommu/omap: add support for late attachment of iommu devices 2019-08-09 17:37:10 +02:00
omap-iopgtable.h iommu/omap: Fix -Woverflow warnings when compiling on 64-bit architectures 2020-03-04 16:24:46 +01:00
rockchip-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
s390-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
sprd-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
sun50i-iommu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
tegra-gart.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
tegra-smmu.c iommu: Streamline registration interface 2021-04-16 17:20:45 +02:00
virtio-iommu.c iommu/virtio: Add missing MODULE_DEVICE_TABLE 2021-05-18 11:24:18 +02:00