From 77c76392b0e3c613730ef5932348c3156c3de60f Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:52 +0200 Subject: [PATCH 01/21] pc-bios/s390-ccw: Remove duplicate blk_factor adjustment When using virtio-scsi, we multiply the READ(10) data_size by a block factor twice when building the I/O. This is fine, since it's only 1 for SCSI disks, but let's clean it up. Signed-off-by: Eric Farman Reviewed-by: Christian Borntraeger Message-Id: <20170510155359.32727-2-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/virtio-scsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index d850a8deed..69b7a93b29 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -154,7 +154,7 @@ static bool scsi_read_10(VDev *vdev, VirtioCmd read_10[] = { { &req, sizeof(req), VRING_DESC_F_NEXT }, { &resp, sizeof(resp), VRING_DESC_F_WRITE | VRING_DESC_F_NEXT }, - { data, data_size * f, VRING_DESC_F_WRITE }, + { data, data_size, VRING_DESC_F_WRITE }, }; debug_print_int("read_10 sector", sector); From 98d3c524359fda04337c8369b617f2d5ef37bf5f Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:53 +0200 Subject: [PATCH 02/21] pc-bios/s390-ccw: Move SCSI block factor to outer read Simple refactoring so that the blk_factor adjustment is moved into virtio_scsi_read_many routine, in preparation for another change. Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-3-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/virtio-scsi.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index 69b7a93b29..6d070e2f73 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -142,14 +142,13 @@ static bool scsi_report_luns(VDev *vdev, void *data, uint32_t data_size) } static bool scsi_read_10(VDev *vdev, - ulong sector, int sectors, void *data) + ulong sector, int sectors, void *data, + unsigned int data_size) { - int f = vdev->blk_factor; - unsigned int data_size = sectors * virtio_get_block_size() * f; ScsiCdbRead10 cdb = { .command = 0x28, - .lba = sector * f, - .xfer_length = sectors * f, + .lba = sector, + .xfer_length = sectors, }; VirtioCmd read_10[] = { { &req, sizeof(req), VRING_DESC_F_NEXT }, @@ -255,7 +254,10 @@ static void virtio_scsi_locate_device(VDev *vdev) int virtio_scsi_read_many(VDev *vdev, ulong sector, void *load_addr, int sec_num) { - if (!scsi_read_10(vdev, sector, sec_num, load_addr)) { + int f = vdev->blk_factor; + unsigned int data_size = sec_num * virtio_get_block_size() * f; + + if (!scsi_read_10(vdev, sector * f, sec_num * f, load_addr, data_size)) { virtio_scsi_verify_response(&resp, "virtio-scsi:read_many"); } From 5ffd4a3c2d75db3ed31752d0936f96719ee0257b Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:54 +0200 Subject: [PATCH 03/21] pc-bios/s390-ccw: Break up virtio-scsi read into multiples A virtio-scsi request that goes through the host sd driver and exceeds the maximum transfer size is automatically broken up for us. But the equivalent request going to the sg driver presumes that any length requirements have already been honored. Let's use the max_sectors field on the virtio-scsi controller device, and break up all requests (both sd and sg) to avoid this problem. Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-4-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/s390-ccw.h | 7 +++++++ pc-bios/s390-ccw/virtio-scsi.c | 18 ++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/pc-bios/s390-ccw/s390-ccw.h b/pc-bios/s390-ccw/s390-ccw.h index 07d8cbcb20..2089274842 100644 --- a/pc-bios/s390-ccw/s390-ccw.h +++ b/pc-bios/s390-ccw/s390-ccw.h @@ -42,6 +42,13 @@ typedef unsigned long long __u64; #ifndef NULL #define NULL 0 #endif +#ifndef MIN +#define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif +#ifndef MIN_NON_ZERO +#define MIN_NON_ZERO(a, b) ((a) == 0 ? (b) : \ + ((b) == 0 ? (a) : (MIN(a, b)))) +#endif #include "cio.h" #include "iplb.h" diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index 6d070e2f73..ff65e2ee30 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -202,6 +202,7 @@ static void virtio_scsi_locate_device(VDev *vdev) debug_print_int("config.scsi.max_channel", vdev->config.scsi.max_channel); debug_print_int("config.scsi.max_target ", vdev->config.scsi.max_target); debug_print_int("config.scsi.max_lun ", vdev->config.scsi.max_lun); + debug_print_int("config.scsi.max_sectors", vdev->config.scsi.max_sectors); if (vdev->scsi_device_selected) { sdev->channel = vdev->selected_scsi_device.channel; @@ -254,12 +255,21 @@ static void virtio_scsi_locate_device(VDev *vdev) int virtio_scsi_read_many(VDev *vdev, ulong sector, void *load_addr, int sec_num) { + int sector_count; int f = vdev->blk_factor; - unsigned int data_size = sec_num * virtio_get_block_size() * f; + unsigned int data_size; - if (!scsi_read_10(vdev, sector * f, sec_num * f, load_addr, data_size)) { - virtio_scsi_verify_response(&resp, "virtio-scsi:read_many"); - } + do { + sector_count = MIN_NON_ZERO(sec_num, vdev->config.scsi.max_sectors); + data_size = sector_count * virtio_get_block_size() * f; + if (!scsi_read_10(vdev, sector * f, sector_count * f, load_addr, + data_size)) { + virtio_scsi_verify_response(&resp, "virtio-scsi:read_many"); + } + load_addr += data_size; + sector += sector_count; + sec_num -= sector_count; + } while (sec_num > 0); return 0; } From 9c12359c577c61ed23f07f7f379434cab2aa1ab2 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:55 +0200 Subject: [PATCH 04/21] pc-bios/s390-ccw: Refactor scsi_inquiry function If we want to issue any of the SCSI Inquiry EVPD pages, which we do, we could use this function to issue both types of commands with a little bit of refactoring. Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-5-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/scsi.h | 6 ++++++ pc-bios/s390-ccw/virtio-scsi.c | 10 ++++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/pc-bios/s390-ccw/scsi.h b/pc-bios/s390-ccw/scsi.h index fc830f7e52..83ffaef54e 100644 --- a/pc-bios/s390-ccw/scsi.h +++ b/pc-bios/s390-ccw/scsi.h @@ -26,6 +26,12 @@ #define SCSI_SENSE_KEY_NO_SENSE 0 #define SCSI_SENSE_KEY_UNIT_ATTENTION 6 +/* SCSI Inquiry Types */ +#define SCSI_INQUIRY_STANDARD 0x00U + +/* SCSI Inquiry Pages */ +#define SCSI_INQUIRY_STANDARD_NONE 0x00U + union ScsiLun { uint64_t v64; /* numeric shortcut */ uint8_t v8[8]; /* generic 8 bytes representation */ diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index ff65e2ee30..9d2e14cdf0 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -89,10 +89,13 @@ static void vs_run(const char *title, VirtioCmd *cmd, VDev *vdev, /* SCSI protocol implementation routines */ -static bool scsi_inquiry(VDev *vdev, void *data, uint32_t data_size) +static bool scsi_inquiry(VDev *vdev, uint8_t evpd, uint8_t page, + void *data, uint32_t data_size) { ScsiCdbInquiry cdb = { .command = 0x12, + .b1 = evpd, + .b2 = page, .alloc_len = data_size < 65535 ? data_size : 65535, }; VirtioCmd inquiry[] = { @@ -346,7 +349,10 @@ void virtio_scsi_setup(VDev *vdev) } /* read and cache SCSI INQUIRY response */ - if (!scsi_inquiry(vdev, scsi_inquiry_std_response, + if (!scsi_inquiry(vdev, + SCSI_INQUIRY_STANDARD, + SCSI_INQUIRY_STANDARD_NONE, + scsi_inquiry_std_response, sizeof(scsi_inquiry_std_response))) { virtio_scsi_verify_response(&resp, "virtio-scsi:setup:inquiry"); } From 8edfe85bef669d676ad17cd84b4e3dce43b110e4 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:56 +0200 Subject: [PATCH 05/21] pc-bios/s390-ccw: Get list of supported VPD pages The "Supported Pages" Inquiry EVPD page is mandatory for all SCSI devices, and is used as a gateway for what VPD pages the device actually supports. Let's issue this Inquiry, and dump that list with the debug facility. Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-6-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/scsi.h | 10 ++++++++++ pc-bios/s390-ccw/virtio-scsi.c | 17 +++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/pc-bios/s390-ccw/scsi.h b/pc-bios/s390-ccw/scsi.h index 83ffaef54e..803eff8ae3 100644 --- a/pc-bios/s390-ccw/scsi.h +++ b/pc-bios/s390-ccw/scsi.h @@ -28,9 +28,11 @@ /* SCSI Inquiry Types */ #define SCSI_INQUIRY_STANDARD 0x00U +#define SCSI_INQUIRY_EVPD 0x01U /* SCSI Inquiry Pages */ #define SCSI_INQUIRY_STANDARD_NONE 0x00U +#define SCSI_INQUIRY_EVPD_SUPPORTED_PAGES 0x00U union ScsiLun { uint64_t v64; /* numeric shortcut */ @@ -77,6 +79,14 @@ struct ScsiInquiryStd { } __attribute__((packed)); typedef struct ScsiInquiryStd ScsiInquiryStd; +struct ScsiInquiryEvpdPages { + uint8_t peripheral_qdt; /* b0, use (b0 & 0x1f) to get SCSI_INQ_RDT */ + uint8_t page_code; /* b1 */ + uint16_t page_length; /* b2..b3 length = N-3 */ + uint8_t byte[28]; /* b4..bN Supported EVPD pages (N=31 here) */ +} __attribute__((packed)); +typedef struct ScsiInquiryEvpdPages ScsiInquiryEvpdPages; + struct ScsiCdbInquiry { uint8_t command; /* b0, == 0x12 */ uint8_t b1; /* b1, |= 0x01 (evpd) */ diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index 9d2e14cdf0..e34755c4d4 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -19,6 +19,7 @@ static VirtioScsiCmdReq req; static VirtioScsiCmdResp resp; static uint8_t scsi_inquiry_std_response[256]; +static ScsiInquiryEvpdPages scsi_inquiry_evpd_pages_response; static inline void vs_assert(bool term, const char **msgs) { @@ -319,6 +320,8 @@ void virtio_scsi_setup(VDev *vdev) int retry_test_unit_ready = 3; uint8_t data[256]; uint32_t data_size = sizeof(data); + ScsiInquiryEvpdPages *evpd = &scsi_inquiry_evpd_pages_response; + int i; vdev->scsi_device = &default_scsi_device; virtio_scsi_locate_device(vdev); @@ -363,6 +366,20 @@ void virtio_scsi_setup(VDev *vdev) vdev->scsi_block_size = VIRTIO_ISO_BLOCK_SIZE; } + if (!scsi_inquiry(vdev, + SCSI_INQUIRY_EVPD, + SCSI_INQUIRY_EVPD_SUPPORTED_PAGES, + evpd, + sizeof(*evpd))) { + virtio_scsi_verify_response(&resp, "virtio-scsi:setup:supported_pages"); + } + + debug_print_int("EVPD length", evpd->page_length); + + for (i = 0; i <= evpd->page_length; i++) { + debug_print_int("supported EVPD page", evpd->byte[i]); + } + if (!scsi_read_capacity(vdev, data, data_size)) { virtio_scsi_verify_response(&resp, "virtio-scsi:setup:read_capacity"); } From fe921fc8b7e92020bb140079a9f47f14fb8e9075 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:57 +0200 Subject: [PATCH 06/21] pc-bios/s390-ccw: Get Block Limits VPD device data The "Block Limits" Inquiry VPD page is optional for any SCSI device, but if it's supported it provides a hint of the maximum I/O transfer length for this particular device. If this page is supported by the disk, let's issue that Inquiry and use the minimum of it and the SCSI controller limit. That will cover this scenario: qemu-system-s390x ... -device virtio-scsi-ccw,id=scsi0,max_sectors=32768 ... -drive file=/dev/sda,if=none,id=drive0,format=raw ... -device scsi-hd,bus=scsi0.0,channel=0,scsi-id=0, drive=drive0,id=disk0,max_io_size=1048576 controller: 32768 sectors x 512 bytes/sector = 16777216 bytes disk: 1048576 bytes Now that we have a limit for a virtio-scsi disk, compare that with the limit for the virtio-scsi controller when we actually build the I/O. The minimum of these two limits should be the one we use. Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-7-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/scsi.h | 14 ++++++++++++++ pc-bios/s390-ccw/virtio-scsi.c | 21 ++++++++++++++++++++- pc-bios/s390-ccw/virtio.h | 1 + 3 files changed, 35 insertions(+), 1 deletion(-) diff --git a/pc-bios/s390-ccw/scsi.h b/pc-bios/s390-ccw/scsi.h index 803eff8ae3..fe3fd5ac05 100644 --- a/pc-bios/s390-ccw/scsi.h +++ b/pc-bios/s390-ccw/scsi.h @@ -33,6 +33,7 @@ /* SCSI Inquiry Pages */ #define SCSI_INQUIRY_STANDARD_NONE 0x00U #define SCSI_INQUIRY_EVPD_SUPPORTED_PAGES 0x00U +#define SCSI_INQUIRY_EVPD_BLOCK_LIMITS 0xb0U union ScsiLun { uint64_t v64; /* numeric shortcut */ @@ -87,6 +88,19 @@ struct ScsiInquiryEvpdPages { } __attribute__((packed)); typedef struct ScsiInquiryEvpdPages ScsiInquiryEvpdPages; +struct ScsiInquiryEvpdBl { + uint8_t peripheral_qdt; /* b0, use (b0 & 0x1f) to get SCSI_INQ_RDT */ + uint8_t page_code; + uint16_t page_length; + uint8_t b4; + uint8_t b5; + uint16_t b6; + uint32_t max_transfer; /* b8 */ + uint32_t b12[7]; /* b12..b43 (defined fields) */ + uint32_t b44[5]; /* b44..b63 (reserved fields) */ +} __attribute__((packed)); +typedef struct ScsiInquiryEvpdBl ScsiInquiryEvpdBl; + struct ScsiCdbInquiry { uint8_t command; /* b0, == 0x12 */ uint8_t b1; /* b1, |= 0x01 (evpd) */ diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index e34755c4d4..b722f25ad7 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -20,6 +20,7 @@ static VirtioScsiCmdResp resp; static uint8_t scsi_inquiry_std_response[256]; static ScsiInquiryEvpdPages scsi_inquiry_evpd_pages_response; +static ScsiInquiryEvpdBl scsi_inquiry_evpd_bl_response; static inline void vs_assert(bool term, const char **msgs) { @@ -262,9 +263,11 @@ int virtio_scsi_read_many(VDev *vdev, int sector_count; int f = vdev->blk_factor; unsigned int data_size; + unsigned int max_transfer = MIN_NON_ZERO(vdev->config.scsi.max_sectors, + vdev->max_transfer); do { - sector_count = MIN_NON_ZERO(sec_num, vdev->config.scsi.max_sectors); + sector_count = MIN_NON_ZERO(sec_num, max_transfer); data_size = sector_count * virtio_get_block_size() * f; if (!scsi_read_10(vdev, sector * f, sector_count * f, load_addr, data_size)) { @@ -321,6 +324,7 @@ void virtio_scsi_setup(VDev *vdev) uint8_t data[256]; uint32_t data_size = sizeof(data); ScsiInquiryEvpdPages *evpd = &scsi_inquiry_evpd_pages_response; + ScsiInquiryEvpdBl *evpd_bl = &scsi_inquiry_evpd_bl_response; int i; vdev->scsi_device = &default_scsi_device; @@ -378,6 +382,21 @@ void virtio_scsi_setup(VDev *vdev) for (i = 0; i <= evpd->page_length; i++) { debug_print_int("supported EVPD page", evpd->byte[i]); + + if (evpd->byte[i] != SCSI_INQUIRY_EVPD_BLOCK_LIMITS) { + continue; + } + + if (!scsi_inquiry(vdev, + SCSI_INQUIRY_EVPD, + SCSI_INQUIRY_EVPD_BLOCK_LIMITS, + evpd_bl, + sizeof(*evpd_bl))) { + virtio_scsi_verify_response(&resp, "virtio-scsi:setup:blocklimits"); + } + + debug_print_int("max transfer", evpd_bl->max_transfer); + vdev->max_transfer = evpd_bl->max_transfer; } if (!scsi_read_capacity(vdev, data, data_size)) { diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h index 3388a423e5..1eaf865b1f 100644 --- a/pc-bios/s390-ccw/virtio.h +++ b/pc-bios/s390-ccw/virtio.h @@ -277,6 +277,7 @@ struct VDev { bool scsi_device_selected; ScsiDevice selected_scsi_device; uint64_t netboot_start_addr; + uint32_t max_transfer; }; typedef struct VDev VDev; From de4e3ae408ad29ca820ae68e09976e14d80289a6 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:58 +0200 Subject: [PATCH 07/21] pc-bios/s390-ccw: Build a reasonable max_sectors limit Now that we've read all the possible limits that have been defined for a virtio-scsi controller and the disk we're booting from, it's possible that we are STILL going to exceed the limits of the host device. For example, a "-device scsi-generic" device does not support the Block Limits VPD page. So, let's fallback to something that seems to work for most boot configurations if larger values were specified (including if nothing was explicitly specified, and we took default values). Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-8-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw/virtio-scsi.c | 9 +++++++++ pc-bios/s390-ccw/virtio-scsi.h | 2 ++ 2 files changed, 11 insertions(+) diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c index b722f25ad7..f61ecf0205 100644 --- a/pc-bios/s390-ccw/virtio-scsi.c +++ b/pc-bios/s390-ccw/virtio-scsi.c @@ -399,6 +399,15 @@ void virtio_scsi_setup(VDev *vdev) vdev->max_transfer = evpd_bl->max_transfer; } + /* + * The host sg driver will often be unhappy with particularly large + * I/Os that exceed the block iovec limits. Let's enforce something + * reasonable, despite what the device configuration tells us. + */ + + vdev->max_transfer = MIN_NON_ZERO(VIRTIO_SCSI_MAX_SECTORS, + vdev->max_transfer); + if (!scsi_read_capacity(vdev, data, data_size)) { virtio_scsi_verify_response(&resp, "virtio-scsi:setup:read_capacity"); } diff --git a/pc-bios/s390-ccw/virtio-scsi.h b/pc-bios/s390-ccw/virtio-scsi.h index f50b38b18b..4c4f4bbc31 100644 --- a/pc-bios/s390-ccw/virtio-scsi.h +++ b/pc-bios/s390-ccw/virtio-scsi.h @@ -19,6 +19,8 @@ #define VIRTIO_SCSI_CDB_SIZE SCSI_DEFAULT_CDB_SIZE #define VIRTIO_SCSI_SENSE_SIZE SCSI_DEFAULT_SENSE_SIZE +#define VIRTIO_SCSI_MAX_SECTORS 2048 + /* command-specific response values */ #define VIRTIO_SCSI_S_OK 0x00 #define VIRTIO_SCSI_S_BAD_TARGET 0x03 From f881bbdf72178166e88fdd8cc8b40e1812efb53c Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Wed, 10 May 2017 17:53:59 +0200 Subject: [PATCH 08/21] pc-bios/s390-ccw.img: rebuild image Contains the following commits: - pc-bios/s390-ccw: Remove duplicate blk_factor adjustment - pc-bios/s390-ccw: Move SCSI block factor to outer read - pc-bios/s390-ccw: Break up virtio-scsi read into multiples - pc-bios/s390-ccw: Refactor scsi_inquiry function - pc-bios/s390-ccw: Get list of supported EVPD pages - pc-bios/s390-ccw: Get Block Limits VPD device data - pc-bios/s390-ccw: Build a reasonable max_sectors limit Signed-off-by: Eric Farman Message-Id: <20170510155359.32727-9-farman@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- pc-bios/s390-ccw.img | Bin 26472 -> 26480 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/pc-bios/s390-ccw.img b/pc-bios/s390-ccw.img index 0b01d49495c607b67d3f1b2359395534631deb88..5ad056400073c7e1c5e862576c76f0e674ff3c60 100644 GIT binary patch delta 7395 zcma)Be_T}6w%_N>FbqFEz%UHM2m_LlDB_P0lypGyk&%sxhDL>k7CuZ;?3LFV?#=5p zuNAWG<}0)5W*xI17lgW4rc)2i-;Rc9MMaL9g)h$-sW+8#zk30_ZrwlLd_Keap7m?* zz1G@m?=ze|Bx#4F`r(qcHv84^@=ivd^3JuL!zDLYq^HuRUhU=mno8?>`O-S>lh#{0 zqnfv#ze$^;fADnX!eM{5J+$Sqm0!=Lt5=A&l2lV zpA#ya@P7%M_9f3Ty(OpI!_SyXCz7+})hYOtAr-b&A>IhyR(QS9!ORQT2%W;_SM1fPb@QsnP?T#CWHGssg z6AmMB4Udh=@Hor`6%|gw4nIdK9>Qlx1GUBBj2yLF#-QvXCHy;q9VdBK>_&Uy1Y%uB;&Q?%BwoqS#15A2OL=tM zWV`JjLK6BFY28EkQ_^zr#c_+}#MAstT!tWuWr*x}l;>NL?Y4(W?{1-&c!hA8z)3rK zt;J=x-Ab$xB-RLLlDL5%vSizB6zWh4b>hb)rcfs>u5NiR6rx30b*uI~aTSway?jjb|Y2s|cH<5S~-(p=*n2HYUV!a|*3GIYm zB&Q}Z^-GVaJD34IV7cfCR%02O$}GiS)87^1y=1YHtd9_;nzVgG*0Z0H{Ix&pt|oa6 z>3&3bfiFZv>rPf^9wj&^{zKe)Tbf zzowC?wfYaFGL!e%?Vg0e*u19&BiPUOa>xQ8S2VB%_9s@E?Rb zNe>u$??P``!w78?{C0$f_VrcxNtlm*U*_{NHZ7m5b|K#U*`&-VmNt6cLL*Nkyoo$U zkjKYFXyc=f8NB8H*KRFaNUxr3#t~jkILH-;!)|$+SWAhOO?VOEPxvIq6psaK!deT6 zHJtD`!hfX^QsIvd8{igUWg^yidKq}^dpUk zt_9V@q?#pqw)-xGpHcX;%AAdiBoLo&tijZzNy@t3`N-dqFb(gTPd`fO zfdOZ|!uV@xgXH)cekiR}j=zPc4|+$o1bN4xzsQ!?nrqW1NwOuZdHZ!)vK;%5=5yCS zC(AJbzG}!Q>4oO)L&i(;fGPZHX0a_MPWb%(7L0wq>nrX4-r7)h@$#W7W#!42PYso1 z#lp`Fn=cPI#iwL-%L5kjqT%nz0}}bw;dA8yQOyt6P9yOXymMr>Cu|_G3?!z0aOoO}X=2|UM^jUpiu>~%*4vcNk+v)>FHxV0#Cfml z-}#7dApU0pCsW-RhX!214BQ15X=hP{)b*l%B8zzS--vebO{1#q<`>A%t?B;imUT%(>~Qs%eeQl(p* zY8Dem4&8Sn`PVt4BEz3R9$psn3AJ+P7?(A?xNoOlz z!kBfD5p6IWCWbNH%^Px;d&Hp`aTj{G?Rbc`RoiN_HpFUM3$wN6LYLMuqr%VBHfDS! zMb}-5_O@zcquh$-1C>DAK&wIhpa#%(P#N@8z^$EN>Fx@x6UfWb0~Ok46s*Fen=%86 z)(VVRjvJ=ECq^o(N_=Iqu~09+sV?^ZuYw}McW=5gOUDV^SmD4ga8|CFD1PT=Uec74{Hyn zf@?k=rd`x7Zk@)4;2nh_E*EJ4V?YTq8q9~aM>5-km|Q~!r1e1se1Fg>{!-vwSh3OV z3}#@(moacFyxF%|*&I@EbD?vw~hVqAc3tuXx z*7Fu$Gv4kAuM!W}^0t}T>e%-Rj#IH%w#isSt^UV=S9JYAqu6$+x-|&z>*_YffLE$F zP_DdUTLvq{wiIEGPgUD=7uJY5mnkvpG3V{j9wS~pdb23XHCz&#F5eai^QM*|qF1i@ zxMOUl=YQTG)HFp+H=t{HjZJPKuTUI!91}rq2tN;u>MQUDT?Ggho{&pCF(Bkf?UqK1 ze2#k`lMpse;NSb|n3Q(_DR31a@Kg!uf$Y925LP#^%W9rSDk@0RSivZbsfkPr)QMUv zh{4mtjL~3D#6uX05~1=Dj>k=N)p%t%#hUTg%hHcW1eKtI@H3Z!>j}16z=;?M%RSJ+ zG_bXlV2PR`n~^xHnu|fno!Pr1u(2ZHzpsob(7rBL5wVEfJ z;c_#rl7)F`MMfm)R(xln2=SJULOTuEb6`v8xb$aRwOtL)mze)z_M9XR}B6} z29y#_gDbSV@J#Gw&F5y!_~_C2pi5y0kQt#X3NW$Cqgb6AJ2jiJ`mRc5gt5zSW_1(i z2bIDKg-t99Dm=WvUL8iKz=Z~c#m9_dHW${277;c{;43FFW4IGJ%I)5nl8yU-oV!ZF zg*}-`z~9jxvmFcdGpAXtl|LuVZx9`Zt^`XplbO}A(6zEe{#1Ulhn&-)cRCXrHBr4q zzl_>06fRtFuXi9cf5aXgrH*4#*C=LSQGvKR#@4zOTn;xg12W1IpTTy)gpY@aJRVI6 zy6R9gP3T#$&Qot;CUq8eK^3E$&`%e@%~bQ4yv<`|bj$8uOErdV?xfb|6s^yMsEeL4 z9i`JMN=1og^%NO&R|RLs&It(g3Ta{N7HFAEEBp@i0da0f^hzSri5H~1e3(tdFGy#k zsX*XUEtrnvQMc&2cTcdJ?@(Q2=*$8Rhvq`%<=lJc%nRQ6`~9_gEk;-zBs{<2ujq(?RNlcXj} zmFmu(`hu87adkIiSeGc|rW)J;L~(moFjHA}u-Kj5R2gtxzz*$NbfHEZ4iiVXB@|YK za3|q~N!PW<$TbzI_OQT4yj0SgJboHd90q+|?|csx%x^Z^)jewWwU@*+O?dghS|?$ex6w0xe!}y3 zJk#agc$YZ+a&rXt{BhD)N%#mYG8ZWnr=5`Q@u=Nb={j%3%Q_fztv2CTAK-UMojTM-KdtJ(R@WlB%&w=G88(8C&(h zgG;LxKf*(APnqyr>5`>2HH#M4&a1qqX3l-{mayMy%&lH@?|)WTEv%|t!mqo1IDg>w z8J>C!I6~K(OYknAuj}s^k>)o*+d$8Oc7SgL#jo*lx~~7d6tohw8gx160nkml-YV?d zb^X2V_@%(2>mQB=-Jt8cTR=N>eeZJAFZlcMY%J0BgYBT}blu~J10xiUI6%8WAqauu zQ4A1L1PXabwXS~*!;m$)ek>id9Ta?%5fu6+2k0r#(YpQ#ihL@7!fjy`<@v=S7Cq04psGr@lYv;(w5*FWEcG&w*qkhw(HJ4!&I z-_ZgJ{V(!CTR^)(PwDze3>1b5oook%en8M#T|ct{v`yE)!34rB3IGhk;pp1~pqqH{ z)HJ!p&8w%5pVs0>a&Sxf`QreB3*y_^q^C?zhZIHoO^PVp{n4Ji`}Q9=c<3;m`^RDV zFvhIEScPb`3ztKRqWuPg^v1v17xonf)WeXRubeO|7V4ohqdP+kri|trXAhD2i}!{$ z_uTE2@SnV9XT>gwcS`0sxmnD26u!N~%FUI{m*-dw^7uVmnU@t?r1Z|FpGKYIZm@s* vuSQ-E_VoH*?S2~O=Kgs*WSQ~$`D5^J#y#^V;IH|<31J8teHys?UfVwb^3>le delta 6738 zcmbtZe^}I2xe3k)y}KOB(|f6*j_XrzOZp|Lh98X((pT{LuCQ3M~;?lUSprEuh*Y2a6-r*vB@^d(qg+aifM^{@8`S&)>Hf6o#z?e z&%E#Fyyu+veb4(nGX&a{-ZsT^yVASS@oHpMDWg|a>BjEcl~SQ9&t~3#Fr@pjRMv;| z%6j2dwpi|Yv^T%TarvPa?)-LNk(j^gWb(!}Ef4clMJW`GhFsgUtU+p4k=kQN#0T)`n)pmBfYuL9Vld3ULRu_OSS8|>b<~N?0zr&4!={> zhV8dyyhy6wdhMV*Px#*@9`U6p2!DfT{8IFUm+_1Yk#DkRr(cu=_Ms%Ce=Bj!=QNP~ z#&ps^XUl3+qr%fR2xCMOw@(mTBJ64DiGCH68vD)#&CF;D_PrT!h1O;Nqv(iOJIlUU zyZ(=BemguHiyc9;bgsS}pQ+U=9=Y7KW1WT|;-Rf$7CB8?on%DMBJ3qxBJuDy#n#AK zJne|+jZEWdZ6Z8sl{NKiNr*a8Y!93vbd;!f3QttOE%hN%&6KLtlZ2;BobiU(7F}ga z9Z#xZWPX!y1exnad`ylzHM+Q_#xB*77m4yD;U1#Q@m|pN8(ytn_sY+!V=pUave?6bPx`gIDMsbJ;?y3I8^6tFoldIT$Xr8sIGLXoJ@MH* zVzvK zw*5)eTb#D!`$=^NnfnQkCG&Hl&El{nQ>aZ8YU?R7Q>bk#g*9OPV5pS+oko>AG@ikIyAoK4D|ChwpOCrfyWlKcOVDvmP z(}Kc&M&|wEX={Zg`Ci#}<~>WKWFk4mH`cY*&_{E3XO zNLA8l!Y`52NV)W@PiXHm1A4$3*%K1Y6=*7zs&BPoewAiSlrttxs_-G1zUEskKB0t|*~FwaXs{E0Mvl7j9k|A!WG3Vi zS0y{zBxZ{w{3y60A$_VfF-dCqmxu!S;(w9$guBGD^vr^IKN*imRpM5{AJA|VD5iP= zK`!rmDNq_}wMidS^?fG}rQghsr+&uiItGwkUiV=bA+E!_;V}lyBS$>M9uKkJn=)(HN0j_9D)E}zn0@IX9+(< z7_Azy7;+vV`f+bS{PP&QP0Ua+@``zzwUK{!RUj#%VY zH<9WwQcWaGr!e7jay1JnLJHyZ2I5XBO*l`ipUV*m7YIK<_z>Ya;4PP*ReF{)dX^`A zMK%I-w;UWZMd7h?#lYB7tC}o*{$nQQ{%7C0KwYRdhJ7rm$34Y| zZG8FsIE4?hik|UHcxw1L9vjzE<9J%JnctRvu01E$AA?&B zFdeg~>%ur;+AQ-^q^cwHZG;y|9QBFBeMOi)UVb*O(q3auZ5dOD<05_`;aS9gM|dU_ z*vvCXl|yD5;Y>1b5Zx0TZu1CI8OTii;OY%B)589K3QbMjQ#zDqbEqj_BzCwQd6oK9 z6rT6G{&z3wO{707amFJuC5BSJGnj+B;3I)v6d`rJ=$kYmQTrFBLt=a0!#2|&$eJx8nTKx6S6pLw| z#2Lx$YT&e;;ixH78boYCnGz)y7Gx-&iPZ&@a>r}+>?uEUMl+AsiAcZXcLuJpta9eF z;!>qs>{>39j~u%1Mv1=`j}3B`$T6_MA_g;a|cU@PFmPM#bXmE^N1|* z*2Jkwq_{M3Q*`8E3>+_~30owZ3fH*hExp1wq7H{(JKme|eiHAu-kQrcXiFJI{MxVm z&4Ff?bt)pTH?S9$(VCUzLH@T(4Yb16&9Yn#f&I{oZ^{Ymb$SBt!N+~Yj)1q=MI+h| zB(ZqE8rZ?IFjm31MKcc&W~nqFsJpzy~Z-FhQn6 z|CL|$MKaH3=8HlA!w+y4haj1Wku4cFzR^ZAh78xptV{|Jz5IuEshJYkT2;$o5TWIrBYO!7huKn z1I&#<2&vyA9aAJywZ|Fz-Z_SzhTSD2fJ7!njL z*K)WS^cv7P=(SoU9J^#rWzZuU;d(za%FN?kf$E8tX}I~He$^AjJn?a8he#N{Vx=Kj znMhVyUovyBn7%mtjmD;XX}ioFaT%r4i!d|e()Pq)A)ZX5nHk|M@-w;1b~R{rA+rv~ zJbksyh`~;unKevb5;RY%QQ7noNT;f3cQHjvWn3Gj_tMDFLd)c`F0V$cuw26Rv;jQS z@ulRb|2~JD1S(}x*9XHLc+T*#jVdmJ8F06b`{HGxSvyTWW;bi~{2(z;AS#S%!KjU8 zW^FRKNi0n~I3>e9m`NEVYFj<3*3UAunfkQ@W;RVaa$*ww48oRz_hy6wnLl7*d2$DR zdCb6K{0Sb$Ho8Sh#{|m6+bXr-BktsLf>INC2afa|h+d zuD8SWSkxLve;M5Pl@*~C`&AbmCD#v+l54P}Ja%*@e~mqsc|MqG$3m65_?_~om3z>k zw#nY4{6+?lcguM$9g^5g&x=bkHq0G9N*XRar@ern?9_Gn=}H3j-b5(&zzEi)9oAob zlCcu>r>h9GL94&ni^5ZE$=KCww$Zxsl_Xqk;&n5^Yc9XG|}{8G)!zA))Cf3rL`q3#!|Zra-u zh~!X>Q$lY?$my(JB~rc2Dt~=D7Fna534pO*?QFhK0@nI4_~T6>Ss~-`BU9>i81QJuEq9 zh91TYjIJ0!>P&zHMHJX)C%C8YL^luskXjNfV<=3A{p zm4Qe6EX8*8Iy;`TS)mq0u`Z-oXSqReXrmR@v<>ajE*nOZ8u%8|6v}X#T4a0%mcqU4 zV5)-x>G(+?O(!JpyP%e$)M_8x^c2U@6%Z{58AsmttiYKGJq5xmRODXWQ|otL+QHmt z|Cj0*+W+)BoXSuzao`q*f`)RUuM*0Wa)RJuS`_Ztz`u~#h_7S1etr_Z^E8&%AaToa zxaw~{gU>IL-A7!y2AZZ2o=$qY1_tjoVuE|b+Pjn7rpM6O0Uk zAF@N&kKyN9BlMr(v#~_ieHO^|y6!#+2SyN1RzqIY^$r-qKy%z_*T343@sBo-15{u%JXvA{FskZ(h7g~a%?Wsv7}w|;gL z033aO5ht-45(7>3y50r7X}hlfB@MCz@;sWlMc2Q;MCKC6^^o9y(GLm!xiyfxbiF$t zvJ1xr6GdP_7c7wA_elA$uJ?999@O=(uz<*DGw$sr0A<26FEf1a7G&d~Xjo_w$LD3+ z_F3^!zK32|3d2!& z8Ba$(6T!QW9lbRSF)$3EEb35h%W3JmFzQo}=z1V`Lc19}`5t;y#__>kP;F* zGa_Z521HRsHg7kJ+KOCv`-&g2Fggs0Y{y&-^WJ(%{W$2i{0lu2*xm~L&RcAXX&4IN zWX+HG)$oHXo%CQY6->lcR@yom!HN9A*m2+>2OSM!U1cus=oN26bUMZP$|=0FRb*A= zPUu7q*rFed!TQ2Gbp5lOAL;XtV6NJcw z>ifJ^lrPNYUCm<6!rA*Cz_Y1WYUAsMq>R6zaH|L}+{P|qn1v4>;?6Q>uy&y{Op%aV!s U?~ZTDRQy#RnyR>j>mmF90k3n$m;e9( From 74c98e20a604b9db58284b8727688df70e9bf643 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 18 May 2017 13:47:27 +0200 Subject: [PATCH 09/21] linux-headers: update Update against Linux v4.12-rc1. Also include the new vfio_ccw.h header. Signed-off-by: Cornelia Huck --- include/standard-headers/asm-x86/hyperv.h | 7 ++++- .../linux/input-event-codes.h | 1 + include/standard-headers/linux/input.h | 11 +++++-- include/standard-headers/linux/pci_regs.h | 3 +- linux-headers/asm-arm/kvm.h | 10 ++++++- linux-headers/asm-arm/unistd-common.h | 1 + linux-headers/asm-arm64/kvm.h | 10 ++++++- linux-headers/asm-powerpc/kvm.h | 3 ++ linux-headers/asm-powerpc/unistd.h | 1 + linux-headers/asm-s390/kvm.h | 29 +++++++++++++++++-- linux-headers/asm-s390/unistd.h | 4 ++- linux-headers/asm-x86/kvm.h | 3 ++ linux-headers/asm-x86/unistd_32.h | 2 ++ linux-headers/asm-x86/unistd_64.h | 1 + linux-headers/asm-x86/unistd_x32.h | 1 + linux-headers/linux/kvm.h | 25 ++++++++++++++++ linux-headers/linux/userfaultfd.h | 11 ++++--- linux-headers/linux/vfio.h | 18 ++++++++++++ linux-headers/linux/vfio_ccw.h | 24 +++++++++++++++ scripts/update-linux-headers.sh | 2 +- 20 files changed, 151 insertions(+), 16 deletions(-) create mode 100644 linux-headers/linux/vfio_ccw.h diff --git a/include/standard-headers/asm-x86/hyperv.h b/include/standard-headers/asm-x86/hyperv.h index eca9a2ca22..d0c6e0a079 100644 --- a/include/standard-headers/asm-x86/hyperv.h +++ b/include/standard-headers/asm-x86/hyperv.h @@ -124,7 +124,7 @@ * Recommend using hypercall for address space switches rather * than MOV to CR3 instruction */ -#define HV_X64_MWAIT_RECOMMENDED (1 << 0) +#define HV_X64_AS_SWITCH_RECOMMENDED (1 << 0) /* Recommend using hypercall for local TLB flushes rather * than INVLPG or MOV to CR3 instructions */ #define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED (1 << 1) @@ -147,6 +147,11 @@ */ #define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) +/* + * Virtual APIC support + */ +#define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) + /* * Crash notification flag. */ diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index c8b3338375..29d463af37 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -641,6 +641,7 @@ * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) */ #define KEY_DATA 0x277 +#define KEY_ONSCREEN_KEYBOARD 0x278 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index b472b8530c..666e201ddb 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -58,9 +58,14 @@ struct input_id { * Note that input core does not clamp reported values to the * [minimum, maximum] limits, such task is left to userspace. * - * Resolution for main axes (ABS_X, ABS_Y, ABS_Z) is reported in - * units per millimeter (units/mm), resolution for rotational axes - * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian. + * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z) + * is reported in units per millimeter (units/mm), resolution + * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported + * in units per radian. + * When INPUT_PROP_ACCELEROMETER is set the resolution changes. + * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in + * in units per g (units/g) and in units per degree per second + * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ). */ struct input_absinfo { int32_t value; diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index 634c9c44ed..d56bb00510 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -114,7 +114,7 @@ #define PCI_SUBSYSTEM_ID 0x2e #define PCI_ROM_ADDRESS 0x30 /* Bits 31..11 are address, 10..1 reserved */ #define PCI_ROM_ADDRESS_ENABLE 0x01 -#define PCI_ROM_ADDRESS_MASK (~0x7ffUL) +#define PCI_ROM_ADDRESS_MASK (~0x7ffU) #define PCI_CAPABILITY_LIST 0x34 /* Offset of first capability list entry */ @@ -630,6 +630,7 @@ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_ARI 0x0020 /* Alternative Routing-ID */ #define PCI_EXP_DEVCTL2_ATOMIC_REQ 0x0040 /* Set Atomic requests */ +#define PCI_EXP_DEVCTL2_ATOMIC_EGRESS_BLOCK 0x0080 /* Block atomic egress */ #define PCI_EXP_DEVCTL2_IDO_REQ_EN 0x0100 /* Allow IDO for requests */ #define PCI_EXP_DEVCTL2_IDO_CMP_EN 0x0200 /* Allow IDO for completions */ #define PCI_EXP_DEVCTL2_LTR_EN 0x0400 /* Enable LTR mechanism */ diff --git a/linux-headers/asm-arm/kvm.h b/linux-headers/asm-arm/kvm.h index 1101d55d2f..7258a00225 100644 --- a/linux-headers/asm-arm/kvm.h +++ b/linux-headers/asm-arm/kvm.h @@ -27,6 +27,8 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -114,6 +116,8 @@ struct kvm_debug_exit_arch { }; struct kvm_sync_regs { + /* Used with KVM_CAP_ARM_USER_IRQ */ + __u64 device_irq_level; }; struct kvm_arch_memory_slot { @@ -192,13 +196,17 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff #define VGIC_LEVEL_INFO_LINE_LEVEL 0 -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 +#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 +#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 diff --git a/linux-headers/asm-arm/unistd-common.h b/linux-headers/asm-arm/unistd-common.h index 13a74afd02..8d5ceaee1a 100644 --- a/linux-headers/asm-arm/unistd-common.h +++ b/linux-headers/asm-arm/unistd-common.h @@ -353,5 +353,6 @@ #define __NR_pkey_mprotect (__NR_SYSCALL_BASE + 394) #define __NR_pkey_alloc (__NR_SYSCALL_BASE + 395) #define __NR_pkey_free (__NR_SYSCALL_BASE + 396) +#define __NR_statx (__NR_SYSCALL_BASE + 397) #endif /* _ASM_ARM_UNISTD_COMMON_H */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index 651ec30040..31bb1dd924 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -39,6 +39,8 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -143,6 +145,8 @@ struct kvm_debug_exit_arch { #define KVM_GUESTDBG_USE_HW (1 << 17) struct kvm_sync_regs { + /* Used with KVM_CAP_ARM_USER_IRQ */ + __u64 device_irq_level; }; struct kvm_arch_memory_slot { @@ -212,13 +216,17 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff #define VGIC_LEVEL_INFO_LINE_LEVEL 0 -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 +#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 +#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h index 4edbe4bb0e..07fbeb9278 100644 --- a/linux-headers/asm-powerpc/kvm.h +++ b/linux-headers/asm-powerpc/kvm.h @@ -29,6 +29,9 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_GUEST_DEBUG +/* Not always available, but if it is, this is the correct offset. */ +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + struct kvm_regs { __u64 pc; __u64 cr; diff --git a/linux-headers/asm-powerpc/unistd.h b/linux-headers/asm-powerpc/unistd.h index 598043c7b6..a1786340e9 100644 --- a/linux-headers/asm-powerpc/unistd.h +++ b/linux-headers/asm-powerpc/unistd.h @@ -393,5 +393,6 @@ #define __NR_preadv2 380 #define __NR_pwritev2 381 #define __NR_kexec_file_load 382 +#define __NR_statx 383 #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h index ac63ca630b..243f195776 100644 --- a/linux-headers/asm-s390/kvm.h +++ b/linux-headers/asm-s390/kvm.h @@ -26,6 +26,8 @@ #define KVM_DEV_FLIC_ADAPTER_REGISTER 6 #define KVM_DEV_FLIC_ADAPTER_MODIFY 7 #define KVM_DEV_FLIC_CLEAR_IO_IRQ 8 +#define KVM_DEV_FLIC_AISM 9 +#define KVM_DEV_FLIC_AIRQ_INJECT 10 /* * We can have up to 4*64k pending subchannels + 8 adapter interrupts, * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts. @@ -41,7 +43,14 @@ struct kvm_s390_io_adapter { __u8 isc; __u8 maskable; __u8 swap; - __u8 pad; + __u8 flags; +}; + +#define KVM_S390_ADAPTER_SUPPRESSIBLE 0x01 + +struct kvm_s390_ais_req { + __u8 isc; + __u16 mode; }; #define KVM_S390_IO_ADAPTER_MASK 1 @@ -110,6 +119,7 @@ struct kvm_s390_vm_cpu_machine { #define KVM_S390_VM_CPU_FEAT_CMMA 10 #define KVM_S390_VM_CPU_FEAT_PFMFI 11 #define KVM_S390_VM_CPU_FEAT_SIGPIF 12 +#define KVM_S390_VM_CPU_FEAT_KSS 13 struct kvm_s390_vm_cpu_feat { __u64 feat[16]; }; @@ -131,7 +141,8 @@ struct kvm_s390_vm_cpu_subfunc { __u8 kmo[16]; /* with MSA4 */ __u8 pcc[16]; /* with MSA4 */ __u8 ppno[16]; /* with MSA5 */ - __u8 reserved[1824]; + __u8 kma[16]; /* with MSA8 */ + __u8 reserved[1808]; }; /* kvm attributes for crypto */ @@ -197,6 +208,10 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_VRS (1UL << 6) #define KVM_SYNC_RICCB (1UL << 7) #define KVM_SYNC_FPRS (1UL << 8) +#define KVM_SYNC_GSCB (1UL << 9) +/* length and alignment of the sdnx as a power of two */ +#define SDNXC 8 +#define SDNXL (1UL << SDNXC) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -217,8 +232,16 @@ struct kvm_sync_regs { }; __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ - __u8 padding[52]; /* riccb needs to be 64byte aligned */ + __u8 padding1[52]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ + __u8 padding2[192]; /* sdnx needs to be 256byte aligned */ + union { + __u8 sdnx[SDNXL]; /* state description annex */ + struct { + __u64 reserved1[2]; + __u64 gscb[4]; + }; + }; }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/linux-headers/asm-s390/unistd.h b/linux-headers/asm-s390/unistd.h index 8a404fd3a1..65e7e59dbb 100644 --- a/linux-headers/asm-s390/unistd.h +++ b/linux-headers/asm-s390/unistd.h @@ -313,7 +313,9 @@ #define __NR_copy_file_range 375 #define __NR_preadv2 376 #define __NR_pwritev2 377 -#define NR_syscalls 378 +#define __NR_s390_guarded_storage 378 +#define __NR_statx 379 +#define NR_syscalls 380 /* * There are some system calls that are not present on 64 bit, some diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 739c0c5940..c2824d02ba 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -9,6 +9,9 @@ #include #include +#define KVM_PIO_PAGE_OFFSET 1 +#define KVM_COALESCED_MMIO_PAGE_OFFSET 2 + #define DE_VECTOR 0 #define DB_VECTOR 1 #define BP_VECTOR 3 diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h index d45ea28e15..8a206df454 100644 --- a/linux-headers/asm-x86/unistd_32.h +++ b/linux-headers/asm-x86/unistd_32.h @@ -380,5 +380,7 @@ #define __NR_pkey_mprotect 380 #define __NR_pkey_alloc 381 #define __NR_pkey_free 382 +#define __NR_statx 383 +#define __NR_arch_prctl 384 #endif /* _ASM_X86_UNISTD_32_H */ diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index e22db9171e..336c2e4aaa 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -333,5 +333,6 @@ #define __NR_pkey_mprotect 329 #define __NR_pkey_alloc 330 #define __NR_pkey_free 331 +#define __NR_statx 332 #endif /* _ASM_X86_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 84e58b202d..cb98a52998 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -286,6 +286,7 @@ #define __NR_pkey_mprotect (__X32_SYSCALL_BIT + 329) #define __NR_pkey_alloc (__X32_SYSCALL_BIT + 330) #define __NR_pkey_free (__X32_SYSCALL_BIT + 331) +#define __NR_statx (__X32_SYSCALL_BIT + 332) #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) #define __NR_ioctl (__X32_SYSCALL_BIT + 514) diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 4e082a81b4..d2892da172 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -702,6 +702,10 @@ struct kvm_ppc_resize_hpt { #define KVM_VM_PPC_HV 1 #define KVM_VM_PPC_PR 2 +/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */ +#define KVM_VM_MIPS_TE 0 +#define KVM_VM_MIPS_VZ 1 + #define KVM_S390_SIE_PAGE_OFFSET 1 /* @@ -883,6 +887,14 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_MMU_RADIX 134 #define KVM_CAP_PPC_MMU_HASH_V3 135 #define KVM_CAP_IMMEDIATE_EXIT 136 +#define KVM_CAP_MIPS_VZ 137 +#define KVM_CAP_MIPS_TE 138 +#define KVM_CAP_MIPS_64BIT 139 +#define KVM_CAP_S390_GS 140 +#define KVM_CAP_S390_AIS 141 +#define KVM_CAP_SPAPR_TCE_VFIO 142 +#define KVM_CAP_X86_GUEST_MWAIT 143 +#define KVM_CAP_ARM_USER_IRQ 144 #ifdef KVM_CAP_IRQ_ROUTING @@ -1087,6 +1099,7 @@ struct kvm_device_attr { #define KVM_DEV_VFIO_GROUP 1 #define KVM_DEV_VFIO_GROUP_ADD 1 #define KVM_DEV_VFIO_GROUP_DEL 2 +#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3 enum kvm_device_type { KVM_DEV_TYPE_FSL_MPIC_20 = 1, @@ -1108,6 +1121,11 @@ enum kvm_device_type { KVM_DEV_TYPE_MAX, }; +struct kvm_vfio_spapr_tce { + __s32 groupfd; + __s32 tablefd; +}; + /* * ioctls for VM fds */ @@ -1354,4 +1372,11 @@ struct kvm_assigned_msix_entry { #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) +/* Available with KVM_CAP_ARM_USER_IRQ */ + +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + #endif /* __LINUX_KVM_H */ diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h index 2ed5dc3775..9701772497 100644 --- a/linux-headers/linux/userfaultfd.h +++ b/linux-headers/linux/userfaultfd.h @@ -20,7 +20,8 @@ #define UFFD_API ((__u64)0xAA) #define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ - UFFD_FEATURE_EVENT_MADVDONTNEED | \ + UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM) #define UFFD_API_IOCTLS \ @@ -92,7 +93,7 @@ struct uffd_msg { struct { __u64 start; __u64 end; - } madv_dn; + } remove; struct { /* unused reserved fields */ @@ -109,7 +110,8 @@ struct uffd_msg { #define UFFD_EVENT_PAGEFAULT 0x12 #define UFFD_EVENT_FORK 0x13 #define UFFD_EVENT_REMAP 0x14 -#define UFFD_EVENT_MADVDONTNEED 0x15 +#define UFFD_EVENT_REMOVE 0x15 +#define UFFD_EVENT_UNMAP 0x16 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -155,9 +157,10 @@ struct uffdio_api { #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) #define UFFD_FEATURE_EVENT_REMAP (1<<2) -#define UFFD_FEATURE_EVENT_MADVDONTNEED (1<<3) +#define UFFD_FEATURE_EVENT_REMOVE (1<<3) #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) +#define UFFD_FEATURE_EVENT_UNMAP (1<<6) __u64 features; __u64 ioctls; diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index 531cb2eda9..4e7ab4c52a 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -198,6 +198,7 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_PCI (1 << 1) /* vfio-pci device */ #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform device */ #define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */ +#define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */ __u32 num_regions; /* Max region index + 1 */ __u32 num_irqs; /* Max IRQ index + 1 */ }; @@ -212,6 +213,7 @@ struct vfio_device_info { #define VFIO_DEVICE_API_PCI_STRING "vfio-pci" #define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform" #define VFIO_DEVICE_API_AMBA_STRING "vfio-amba" +#define VFIO_DEVICE_API_CCW_STRING "vfio-ccw" /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, @@ -446,6 +448,22 @@ enum { VFIO_PCI_NUM_IRQS }; +/* + * The vfio-ccw bus driver makes use of the following fixed region and + * IRQ index mapping. Unimplemented regions return a size of zero. + * Unimplemented IRQ types return a count of zero. + */ + +enum { + VFIO_CCW_CONFIG_REGION_INDEX, + VFIO_CCW_NUM_REGIONS +}; + +enum { + VFIO_CCW_IO_IRQ_INDEX, + VFIO_CCW_NUM_IRQS +}; + /** * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12, * struct vfio_pci_hot_reset_info) diff --git a/linux-headers/linux/vfio_ccw.h b/linux-headers/linux/vfio_ccw.h new file mode 100644 index 0000000000..3a565511ab --- /dev/null +++ b/linux-headers/linux/vfio_ccw.h @@ -0,0 +1,24 @@ +/* + * Interfaces for vfio-ccw + * + * Copyright IBM Corp. 2017 + * + * Author(s): Dong Jia Shi + */ + +#ifndef _VFIO_CCW_H_ +#define _VFIO_CCW_H_ + +#include + +struct ccw_io_region { +#define ORB_AREA_SIZE 12 + __u8 orb_area[ORB_AREA_SIZE]; +#define SCSW_AREA_SIZE 12 + __u8 scsw_area[SCSW_AREA_SIZE]; +#define IRB_AREA_SIZE 96 + __u8 irb_area[IRB_AREA_SIZE]; + __u32 ret_code; +} __attribute__((packed)); + +#endif diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index 6a370a8669..2f906c4d16 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -113,7 +113,7 @@ done rm -rf "$output/linux-headers/linux" mkdir -p "$output/linux-headers/linux" -for header in kvm.h kvm_para.h vfio.h vhost.h \ +for header in kvm.h kvm_para.h vfio.h vfio_ccw.h vhost.h \ psci.h userfaultfd.h; do cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux" done From 274250c30158f60aefb46088a7bb0d711061226c Mon Sep 17 00:00:00 2001 From: Xiao Feng Ren Date: Wed, 17 May 2017 02:48:03 +0200 Subject: [PATCH 10/21] s390x/css: add s390-squash-mcss machine option We want to support real (i.e. not virtual) channel devices even for guests that do not support MCSS-E (where guests may see devices from any channel subsystem image at once). As all virtio-ccw devices are in css 0xfe (and show up in the default css 0 for guests not activating MCSS-E), we need an option to squash both the virtio subchannels and e.g. passed-through subchannels from their real css (0-3, or 0 for hosts not activating MCSS-E) into the default css. This will be exploited in a later patch. Signed-off-by: Xiao Feng Ren Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-4-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/s390-virtio-ccw.c | 21 +++++++++++++++++++++ include/hw/s390x/s390-virtio-ccw.h | 1 + qemu-options.hx | 6 +++++- target/s390x/cpu.h | 10 ++++++++++ 4 files changed, 37 insertions(+), 1 deletion(-) diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index fdd4384ff0..cd007ca8cf 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -303,6 +303,20 @@ static void machine_set_loadparm(Object *obj, const char *val, Error **errp) ms->loadparm[i] = ' '; /* pad right with spaces */ } } +static inline bool machine_get_squash_mcss(Object *obj, Error **errp) +{ + S390CcwMachineState *ms = S390_CCW_MACHINE(obj); + + return ms->s390_squash_mcss; +} + +static inline void machine_set_squash_mcss(Object *obj, bool value, + Error **errp) +{ + S390CcwMachineState *ms = S390_CCW_MACHINE(obj); + + ms->s390_squash_mcss = value; +} static inline void s390_machine_initfn(Object *obj) { @@ -328,6 +342,13 @@ static inline void s390_machine_initfn(Object *obj) " to upper case) to pass to machine loader, boot manager," " and guest kernel", NULL); + object_property_add_bool(obj, "s390-squash-mcss", + machine_get_squash_mcss, + machine_set_squash_mcss, NULL); + object_property_set_description(obj, "s390-squash-mcss", + "enable/disable squashing subchannels into the default css", + NULL); + object_property_set_bool(obj, false, "s390-squash-mcss", NULL); } static const TypeInfo ccw_machine_info = { diff --git a/include/hw/s390x/s390-virtio-ccw.h b/include/hw/s390x/s390-virtio-ccw.h index 7b8a3e4d74..3027555f6d 100644 --- a/include/hw/s390x/s390-virtio-ccw.h +++ b/include/hw/s390x/s390-virtio-ccw.h @@ -29,6 +29,7 @@ typedef struct S390CcwMachineState { bool aes_key_wrap; bool dea_key_wrap; uint8_t loadparm[8]; + bool s390_squash_mcss; } S390CcwMachineState; typedef struct S390CcwMachineClass { diff --git a/qemu-options.hx b/qemu-options.hx index f07a310eb1..1e5382c1e1 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -42,7 +42,8 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \ " dea-key-wrap=on|off controls support for DEA key wrapping (default=on)\n" " suppress-vmdesc=on|off disables self-describing migration (default=off)\n" " nvdimm=on|off controls NVDIMM support (default=off)\n" - " enforce-config-section=on|off enforce configuration section migration (default=off)\n", + " enforce-config-section=on|off enforce configuration section migration (default=off)\n" + " s390-squash-mcss=on|off controls support for squashing into default css (default=off)\n", QEMU_ARCH_ALL) STEXI @item -machine [type=]@var{name}[,prop=@var{value}[,...]] @@ -81,6 +82,9 @@ controls whether DEA wrapping keys will be created to allow execution of DEA cryptographic functions. The default is on. @item nvdimm=on|off Enables or disables NVDIMM support. The default is off. +@item s390-squash-mcss=on|off +Enables or disables squashing subchannels into the default css. +The default is off. @end table ETEXI diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index 240b8a5c22..e27d9d874a 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -1256,6 +1256,16 @@ static inline void s390_crypto_reset(void) } } +static inline bool s390_get_squash_mcss(void) +{ + if (object_property_get_bool(OBJECT(qdev_get_machine()), "s390-squash-mcss", + NULL)) { + return true; + } + + return false; +} + /* machine check interruption code */ /* subclasses */ From 8f3cf0128cbac1ac19be8515dc184edb88dd5fb1 Mon Sep 17 00:00:00 2001 From: Xiao Feng Ren Date: Wed, 17 May 2017 02:48:04 +0200 Subject: [PATCH 11/21] s390x/css: realize css_sch_build_schib The S390 virtual css support already has a mechanism to build a virtual subchannel information block (schib) and provide virtual subchannels to the guest. However, to pass-through subchannels to a guest, we need to introduce a new mechanism to build its schib according to the real device information. Thus we realize a new css sch_build_schib function to extract the path_masks, chpids, chpid type from sysfs. To reuse the existing code, we refactor css_add_virtual_chpid to css_add_chpid. Reviewed-by: Pierre Morel Signed-off-by: Xiao Feng Ren Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-5-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/css.c | 152 ++++++++++++++++++++++++++++++++++++++++- include/hw/s390x/css.h | 36 +++++----- 2 files changed, 168 insertions(+), 20 deletions(-) diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 15c4f4b249..2c8d0e7219 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -13,6 +13,7 @@ #include "qapi/error.h" #include "qapi/visitor.h" #include "hw/qdev.h" +#include "qemu/error-report.h" #include "qemu/bitops.h" #include "exec/address-spaces.h" #include "cpu.h" @@ -1326,7 +1327,8 @@ unsigned int css_find_free_chpid(uint8_t cssid) return MAX_CHPID + 1; } -static int css_add_virtual_chpid(uint8_t cssid, uint8_t chpid, uint8_t type) +static int css_add_chpid(uint8_t cssid, uint8_t chpid, uint8_t type, + bool is_virt) { CssImage *css; @@ -1340,7 +1342,7 @@ static int css_add_virtual_chpid(uint8_t cssid, uint8_t chpid, uint8_t type) } css->chpids[chpid].in_use = 1; css->chpids[chpid].type = type; - css->chpids[chpid].is_virtual = 1; + css->chpids[chpid].is_virtual = is_virt; css_generate_chp_crws(cssid, chpid); @@ -1364,7 +1366,7 @@ void css_sch_build_virtual_schib(SubchDev *sch, uint8_t chpid, uint8_t type) p->pam = 0x80; p->chpid[0] = chpid; if (!css->chpids[chpid].in_use) { - css_add_virtual_chpid(sch->cssid, chpid, type); + css_add_chpid(sch->cssid, chpid, type, true); } memset(s, 0, sizeof(SCSW)); @@ -1978,3 +1980,147 @@ SubchDev *css_create_virtual_sch(CssDevId bus_id, Error **errp) css_subch_assign(sch->cssid, sch->ssid, schid, sch->devno, sch); return sch; } + +static int css_sch_get_chpids(SubchDev *sch, CssDevId *dev_id) +{ + char *fid_path; + FILE *fd; + uint32_t chpid[8]; + int i; + PMCW *p = &sch->curr_status.pmcw; + + fid_path = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/chpids", + dev_id->cssid, dev_id->ssid, dev_id->devid); + fd = fopen(fid_path, "r"); + if (fd == NULL) { + error_report("%s: open %s failed", __func__, fid_path); + g_free(fid_path); + return -EINVAL; + } + + if (fscanf(fd, "%x %x %x %x %x %x %x %x", + &chpid[0], &chpid[1], &chpid[2], &chpid[3], + &chpid[4], &chpid[5], &chpid[6], &chpid[7]) != 8) { + fclose(fd); + g_free(fid_path); + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(p->chpid); i++) { + p->chpid[i] = chpid[i]; + } + + fclose(fd); + g_free(fid_path); + + return 0; +} + +static int css_sch_get_path_masks(SubchDev *sch, CssDevId *dev_id) +{ + char *fid_path; + FILE *fd; + uint32_t pim, pam, pom; + PMCW *p = &sch->curr_status.pmcw; + + fid_path = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/pimpampom", + dev_id->cssid, dev_id->ssid, dev_id->devid); + fd = fopen(fid_path, "r"); + if (fd == NULL) { + error_report("%s: open %s failed", __func__, fid_path); + g_free(fid_path); + return -EINVAL; + } + + if (fscanf(fd, "%x %x %x", &pim, &pam, &pom) != 3) { + fclose(fd); + g_free(fid_path); + return -EINVAL; + } + + p->pim = pim; + p->pam = pam; + p->pom = pom; + fclose(fd); + g_free(fid_path); + + return 0; +} + +static int css_sch_get_chpid_type(uint8_t chpid, uint32_t *type, + CssDevId *dev_id) +{ + char *fid_path; + FILE *fd; + + fid_path = g_strdup_printf("/sys/devices/css%x/chp0.%02x/type", + dev_id->cssid, chpid); + fd = fopen(fid_path, "r"); + if (fd == NULL) { + error_report("%s: open %s failed", __func__, fid_path); + g_free(fid_path); + return -EINVAL; + } + + if (fscanf(fd, "%x", type) != 1) { + fclose(fd); + g_free(fid_path); + return -EINVAL; + } + + fclose(fd); + g_free(fid_path); + + return 0; +} + +/* + * We currently retrieve the real device information from sysfs to build the + * guest subchannel information block without considering the migration feature. + * We need to revisit this problem when we want to add migration support. + */ +int css_sch_build_schib(SubchDev *sch, CssDevId *dev_id) +{ + CssImage *css = channel_subsys.css[sch->cssid]; + PMCW *p = &sch->curr_status.pmcw; + SCSW *s = &sch->curr_status.scsw; + uint32_t type; + int i, ret; + + assert(css != NULL); + memset(p, 0, sizeof(PMCW)); + p->flags |= PMCW_FLAGS_MASK_DNV; + /* We are dealing with I/O subchannels only. */ + p->devno = sch->devno; + + /* Grab path mask from sysfs. */ + ret = css_sch_get_path_masks(sch, dev_id); + if (ret) { + return ret; + } + + /* Grab chpids from sysfs. */ + ret = css_sch_get_chpids(sch, dev_id); + if (ret) { + return ret; + } + + /* Build chpid type. */ + for (i = 0; i < ARRAY_SIZE(p->chpid); i++) { + if (p->chpid[i] && !css->chpids[p->chpid[i]].in_use) { + ret = css_sch_get_chpid_type(p->chpid[i], &type, dev_id); + if (ret) { + return ret; + } + css_add_chpid(sch->cssid, p->chpid[i], type, false); + } + } + + memset(s, 0, sizeof(SCSW)); + sch->curr_status.mba = 0; + for (i = 0; i < ARRAY_SIZE(sch->curr_status.mda); i++) { + sch->curr_status.mda[i] = 0; + } + + return 0; +} diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index e61fa74d9b..e59a11537f 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -95,6 +95,24 @@ struct SubchDev { void *driver_data; }; +/* + * Identify a device within the channel subsystem. + * Note that this can be used to identify either the subchannel or + * the attached I/O device, as there's always one I/O device per + * subchannel. + */ +typedef struct CssDevId { + uint8_t cssid; + uint8_t ssid; + uint16_t devid; + bool valid; +} CssDevId; + +extern PropertyInfo css_devid_propinfo; + +#define DEFINE_PROP_CSS_DEV_ID(_n, _s, _f) \ + DEFINE_PROP(_n, _s, _f, css_devid_propinfo, CssDevId) + typedef struct IndAddr { hwaddr addr; uint64_t map; @@ -116,6 +134,7 @@ bool css_devno_used(uint8_t cssid, uint8_t ssid, uint16_t devno); void css_subch_assign(uint8_t cssid, uint8_t ssid, uint16_t schid, uint16_t devno, SubchDev *sch); void css_sch_build_virtual_schib(SubchDev *sch, uint8_t chpid, uint8_t type); +int css_sch_build_schib(SubchDev *sch, CssDevId *dev_id); unsigned int css_find_free_chpid(uint8_t cssid); uint16_t css_build_subchannel_id(SubchDev *sch); void css_reset(void); @@ -164,23 +183,6 @@ int css_do_rsch(SubchDev *sch); int css_do_rchp(uint8_t cssid, uint8_t chpid); bool css_present(uint8_t cssid); #endif -/* - * Identify a device within the channel subsystem. - * Note that this can be used to identify either the subchannel or - * the attached I/O device, as there's always one I/O device per - * subchannel. - */ -typedef struct CssDevId { - uint8_t cssid; - uint8_t ssid; - uint16_t devid; - bool valid; -} CssDevId; - -extern PropertyInfo css_devid_propinfo; - -#define DEFINE_PROP_CSS_DEV_ID(_n, _s, _f) \ - DEFINE_PROP(_n, _s, _f, css_devid_propinfo, CssDevId) extern PropertyInfo css_devid_ro_propinfo; From 817d4a6bc8bc6c2ad57ffdbab1a33c9b930ddde4 Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:05 +0200 Subject: [PATCH 12/21] s390x/css: realize css_create_sch The S390 virtual css support already has a mechanism to create a virtual subchannel and provide it to the guest. However, to pass-through subchannels to a guest, we need to introduce a new mechanism to create the subchannel according to the real device information. Thus we reconstruct css_create_virtual_sch to a new css_create_sch function to handle all these cases and do allocation and initialization of the subchannel according to the device type and machine configuration. Reviewed-by: Pierre Morel Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-6-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/3270-ccw.c | 6 ++++- hw/s390x/css-bridge.c | 2 ++ hw/s390x/css.c | 45 +++++++++++++++++++++++++++++------ hw/s390x/s390-virtio-ccw.c | 11 ++++++--- hw/s390x/virtio-ccw.c | 6 ++++- include/hw/s390x/css-bridge.h | 1 + include/hw/s390x/css.h | 25 ++++++++++++------- 7 files changed, 76 insertions(+), 20 deletions(-) diff --git a/hw/s390x/3270-ccw.c b/hw/s390x/3270-ccw.c index a7a5b412e4..6e6eee4e90 100644 --- a/hw/s390x/3270-ccw.c +++ b/hw/s390x/3270-ccw.c @@ -98,9 +98,13 @@ static void emulated_ccw_3270_realize(DeviceState *ds, Error **errp) EmulatedCcw3270Class *ck = EMULATED_CCW_3270_GET_CLASS(dev); CcwDevice *cdev = CCW_DEVICE(ds); CCWDeviceClass *cdk = CCW_DEVICE_GET_CLASS(cdev); - SubchDev *sch = css_create_virtual_sch(cdev->devno, errp); + DeviceState *parent = DEVICE(cdev); + BusState *qbus = qdev_get_parent_bus(parent); + VirtualCssBus *cbus = VIRTUAL_CSS_BUS(qbus); + SubchDev *sch; Error *err = NULL; + sch = css_create_sch(cdev->devno, true, cbus->squash_mcss, errp); if (!sch) { return; } diff --git a/hw/s390x/css-bridge.c b/hw/s390x/css-bridge.c index b54ac01d37..823747fcd7 100644 --- a/hw/s390x/css-bridge.c +++ b/hw/s390x/css-bridge.c @@ -17,6 +17,7 @@ #include "hw/s390x/css.h" #include "ccw-device.h" #include "hw/s390x/css-bridge.h" +#include "cpu.h" /* * Invoke device-specific unplug handler, disable the subchannel @@ -103,6 +104,7 @@ VirtualCssBus *virtual_css_bus_init(void) /* Create bus on bridge device */ bus = qbus_create(TYPE_VIRTUAL_CSS_BUS, dev, "virtual-css"); cbus = VIRTUAL_CSS_BUS(bus); + cbus->squash_mcss = s390_get_squash_mcss(); /* Enable hotplugging */ qbus_set_hotplug_handler(bus, dev, &error_abort); diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 2c8d0e7219..a8aed9cb3a 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -1948,28 +1948,59 @@ PropertyInfo css_devid_ro_propinfo = { .get = get_css_devid, }; -SubchDev *css_create_virtual_sch(CssDevId bus_id, Error **errp) +SubchDev *css_create_sch(CssDevId bus_id, bool is_virtual, bool squash_mcss, + Error **errp) { uint16_t schid = 0; SubchDev *sch; if (bus_id.valid) { - /* Enforce use of virtual cssid. */ - if (bus_id.cssid != VIRTUAL_CSSID) { - error_setg(errp, "cssid %hhx not valid for virtual devices", - bus_id.cssid); + if (is_virtual != (bus_id.cssid == VIRTUAL_CSSID)) { + error_setg(errp, "cssid %hhx not valid for %s devices", + bus_id.cssid, + (is_virtual ? "virtual" : "non-virtual")); return NULL; } + } + + if (bus_id.valid) { + if (squash_mcss) { + bus_id.cssid = channel_subsys.default_cssid; + } else if (!channel_subsys.css[bus_id.cssid]) { + css_create_css_image(bus_id.cssid, false); + } + if (!css_find_free_subch_for_devno(bus_id.cssid, bus_id.ssid, bus_id.devid, &schid, errp)) { return NULL; } - } else { - bus_id.cssid = VIRTUAL_CSSID; + } else if (squash_mcss || is_virtual) { + bus_id.cssid = channel_subsys.default_cssid; + if (!css_find_free_subch_and_devno(bus_id.cssid, &bus_id.ssid, &bus_id.devid, &schid, errp)) { return NULL; } + } else { + for (bus_id.cssid = 0; bus_id.cssid < MAX_CSSID; ++bus_id.cssid) { + if (bus_id.cssid == VIRTUAL_CSSID) { + continue; + } + + if (!channel_subsys.css[bus_id.cssid]) { + css_create_css_image(bus_id.cssid, false); + } + + if (css_find_free_subch_and_devno(bus_id.cssid, &bus_id.ssid, + &bus_id.devid, &schid, + NULL)) { + break; + } + if (bus_id.cssid == MAX_CSSID) { + error_setg(errp, "Virtual channel subsystem is full!"); + return NULL; + } + } } sch = g_malloc0(sizeof(*sch)); diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index cd007ca8cf..c9021f2fa9 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -136,10 +136,15 @@ static void ccw_init(MachineState *machine) kvm_s390_enable_css_support(s390_cpu_addr2state(0)); } /* - * Create virtual css and set it as default so that non mcss-e - * enabled guests only see virtio devices. + * Non mcss-e enabled guests only see the devices from the default + * css, which is determined by the value of the squash_mcss property. + * Note: we must not squash non virtual devices to css 0xFE. */ - ret = css_create_css_image(VIRTUAL_CSSID, true); + if (css_bus->squash_mcss) { + ret = css_create_css_image(0, true); + } else { + ret = css_create_css_image(VIRTUAL_CSSID, true); + } assert(ret == 0); /* Create VirtIO network adapters */ diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index e7167e3d05..4e386e9781 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -680,9 +680,13 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp) VirtIOCCWDeviceClass *k = VIRTIO_CCW_DEVICE_GET_CLASS(dev); CcwDevice *ccw_dev = CCW_DEVICE(dev); CCWDeviceClass *ck = CCW_DEVICE_GET_CLASS(ccw_dev); - SubchDev *sch = css_create_virtual_sch(ccw_dev->devno, errp); + DeviceState *parent = DEVICE(ccw_dev); + BusState *qbus = qdev_get_parent_bus(parent); + VirtualCssBus *cbus = VIRTUAL_CSS_BUS(qbus); + SubchDev *sch; Error *err = NULL; + sch = css_create_sch(ccw_dev->devno, true, cbus->squash_mcss, errp); if (!sch) { return; } diff --git a/include/hw/s390x/css-bridge.h b/include/hw/s390x/css-bridge.h index 5a0203be5f..cf0860432a 100644 --- a/include/hw/s390x/css-bridge.h +++ b/include/hw/s390x/css-bridge.h @@ -28,6 +28,7 @@ typedef struct VirtualCssBridge { /* virtual css bus type */ typedef struct VirtualCssBus { BusState parent_obj; + bool squash_mcss; } VirtualCssBus; #define TYPE_VIRTUAL_CSS_BUS "virtual-css-bus" diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index e59a11537f..60ff83e9c1 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -192,16 +192,25 @@ extern PropertyInfo css_devid_ro_propinfo; /** * Create a subchannel for the given bus id. * - * If @p bus_id is valid, verify that it uses the virtual channel - * subsystem id and is not already in use, and find a free subchannel - * id for it. If @p bus_id is not valid, find a free subchannel id and - * device number across all subchannel sets. If either of the former - * actions succeed, allocate a subchannel structure, initialise it - * with the bus id, subchannel id and device number, register it with - * the CSS and return it. Otherwise return NULL. + * If @p bus_id is valid, and @p squash_mcss is true, verify that it is + * not already in use in the default css, and find a free devno from the + * default css image for it. + * If @p bus_id is valid, and @p squash_mcss is false, verify that it is + * not already in use, and find a free devno for it. + * If @p bus_id is not valid, and if either @p squash_mcss or @p is_virtual + * is true, find a free subchannel id and device number across all + * subchannel sets from the default css image. + * If @p bus_id is not valid, and if both @p squash_mcss and @p is_virtual + * are false, find a non-full css image and find a free subchannel id and + * device number across all subchannel sets from it. + * + * If either of the former actions succeed, allocate a subchannel structure, + * initialise it with the bus id, subchannel id and device number, register + * it with the CSS and return it. Otherwise return NULL. * * The caller becomes owner of the returned subchannel structure and * is responsible for unregistering and freeing it. */ -SubchDev *css_create_virtual_sch(CssDevId bus_id, Error **errp); +SubchDev *css_create_sch(CssDevId bus_id, bool is_virtual, bool squash_mcss, + Error **errp); #endif From a8eac9431ad060012348908f93d6421ae3c97300 Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:06 +0200 Subject: [PATCH 13/21] s390x/css: device support for s390-ccw passthrough In order to support subchannels pass-through, we introduce a s390 subchannel device called "s390-ccw" to hold the real subchannel info. The s390-ccw devices inherit from the abstract CcwDevice which connect to the existing virtual-css-bus. Reviewed-by: Eric Auger Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-7-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/Makefile.objs | 1 + hw/s390x/s390-ccw.c | 141 ++++++++++++++++++++++++++++++++++++ include/hw/s390x/s390-ccw.h | 38 ++++++++++ 3 files changed, 180 insertions(+) create mode 100644 hw/s390x/s390-ccw.c create mode 100644 include/hw/s390x/s390-ccw.h diff --git a/hw/s390x/Makefile.objs b/hw/s390x/Makefile.objs index 36bd4b1645..a8e5575a8a 100644 --- a/hw/s390x/Makefile.objs +++ b/hw/s390x/Makefile.objs @@ -14,3 +14,4 @@ obj-y += ccw-device.o obj-y += s390-pci-bus.o s390-pci-inst.o obj-y += s390-skeys.o obj-$(CONFIG_KVM) += s390-skeys-kvm.o +obj-y += s390-ccw.o diff --git a/hw/s390x/s390-ccw.c b/hw/s390x/s390-ccw.c new file mode 100644 index 0000000000..e2b1973fda --- /dev/null +++ b/hw/s390x/s390-ccw.c @@ -0,0 +1,141 @@ +/* + * s390 CCW Assignment Support + * + * Copyright 2017 IBM Corp + * Author(s): Dong Jia Shi + * Xiao Feng Ren + * Pierre Morel + * + * This work is licensed under the terms of the GNU GPL, version 2 + * or (at your option) any later version. See the COPYING file in the + * top-level directory. + */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/sysbus.h" +#include "libgen.h" +#include "hw/s390x/css.h" +#include "hw/s390x/css-bridge.h" +#include "hw/s390x/s390-ccw.h" + +static void s390_ccw_get_dev_info(S390CCWDevice *cdev, + char *sysfsdev, + Error **errp) +{ + unsigned int cssid, ssid, devid; + char dev_path[PATH_MAX] = {0}, *tmp; + + if (!sysfsdev) { + error_setg(errp, "No host device provided"); + error_append_hint(errp, + "Use -device vfio-ccw,sysfsdev=PATH_TO_DEVICE\n"); + return; + } + + if (!realpath(sysfsdev, dev_path)) { + error_setg_errno(errp, errno, "Host device '%s' not found", sysfsdev); + return; + } + + cdev->mdevid = g_strdup(basename(dev_path)); + + tmp = basename(dirname(dev_path)); + if (sscanf(tmp, "%2x.%1x.%4x", &cssid, &ssid, &devid) != 3) { + error_setg_errno(errp, errno, "Failed to read %s", tmp); + return; + } + + cdev->hostid.cssid = cssid; + cdev->hostid.ssid = ssid; + cdev->hostid.devid = devid; + cdev->hostid.valid = true; +} + +static void s390_ccw_realize(S390CCWDevice *cdev, char *sysfsdev, Error **errp) +{ + CcwDevice *ccw_dev = CCW_DEVICE(cdev); + CCWDeviceClass *ck = CCW_DEVICE_GET_CLASS(ccw_dev); + DeviceState *parent = DEVICE(ccw_dev); + BusState *qbus = qdev_get_parent_bus(parent); + VirtualCssBus *cbus = VIRTUAL_CSS_BUS(qbus); + SubchDev *sch; + int ret; + Error *err = NULL; + + s390_ccw_get_dev_info(cdev, sysfsdev, &err); + if (err) { + goto out_err_propagate; + } + + sch = css_create_sch(ccw_dev->devno, false, cbus->squash_mcss, &err); + if (!sch) { + goto out_mdevid_free; + } + sch->driver_data = cdev; + + ccw_dev->sch = sch; + ret = css_sch_build_schib(sch, &cdev->hostid); + if (ret) { + error_setg_errno(&err, -ret, "%s: Failed to build initial schib", + __func__); + goto out_err; + } + + ck->realize(ccw_dev, &err); + if (err) { + goto out_err; + } + + css_generate_sch_crws(sch->cssid, sch->ssid, sch->schid, + parent->hotplugged, 1); + return; + +out_err: + css_subch_assign(sch->cssid, sch->ssid, sch->schid, sch->devno, NULL); + ccw_dev->sch = NULL; + g_free(sch); +out_mdevid_free: + g_free(cdev->mdevid); +out_err_propagate: + error_propagate(errp, err); +} + +static void s390_ccw_unrealize(S390CCWDevice *cdev, Error **errp) +{ + CcwDevice *ccw_dev = CCW_DEVICE(cdev); + SubchDev *sch = ccw_dev->sch; + + if (sch) { + css_subch_assign(sch->cssid, sch->ssid, sch->schid, sch->devno, NULL); + g_free(sch); + ccw_dev->sch = NULL; + } + + g_free(cdev->mdevid); +} + +static void s390_ccw_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + S390CCWDeviceClass *cdc = S390_CCW_DEVICE_CLASS(klass); + + dc->bus_type = TYPE_VIRTUAL_CSS_BUS; + cdc->realize = s390_ccw_realize; + cdc->unrealize = s390_ccw_unrealize; +} + +static const TypeInfo s390_ccw_info = { + .name = TYPE_S390_CCW, + .parent = TYPE_CCW_DEVICE, + .instance_size = sizeof(S390CCWDevice), + .class_size = sizeof(S390CCWDeviceClass), + .class_init = s390_ccw_class_init, + .abstract = true, +}; + +static void register_s390_ccw_type(void) +{ + type_register_static(&s390_ccw_info); +} + +type_init(register_s390_ccw_type) diff --git a/include/hw/s390x/s390-ccw.h b/include/hw/s390x/s390-ccw.h new file mode 100644 index 0000000000..b58d8e9ca3 --- /dev/null +++ b/include/hw/s390x/s390-ccw.h @@ -0,0 +1,38 @@ +/* + * s390 CCW Assignment Support + * + * Copyright 2017 IBM Corp. + * Author(s): Dong Jia Shi + * Xiao Feng Ren + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#ifndef HW_S390_CCW_H +#define HW_S390_CCW_H + +#include "hw/s390x/ccw-device.h" + +#define TYPE_S390_CCW "s390-ccw" +#define S390_CCW_DEVICE(obj) \ + OBJECT_CHECK(S390CCWDevice, (obj), TYPE_S390_CCW) +#define S390_CCW_DEVICE_CLASS(klass) \ + OBJECT_CLASS_CHECK(S390CCWDeviceClass, (klass), TYPE_S390_CCW) +#define S390_CCW_DEVICE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(S390CCWDeviceClass, (obj), TYPE_S390_CCW) + +typedef struct S390CCWDevice { + CcwDevice parent_obj; + CssDevId hostid; + char *mdevid; +} S390CCWDevice; + +typedef struct S390CCWDeviceClass { + CCWDeviceClass parent_class; + void (*realize)(S390CCWDevice *dev, char *sysfsdev, Error **errp); + void (*unrealize)(S390CCWDevice *dev, Error **errp); +} S390CCWDeviceClass; + +#endif From 1dcac3e15263674bb9c84feed6b35bb1f7bc1c6b Mon Sep 17 00:00:00 2001 From: Xiao Feng Ren Date: Wed, 17 May 2017 02:48:07 +0200 Subject: [PATCH 14/21] vfio/ccw: vfio based subchannel passthrough driver We use the IOMMU_TYPE1 of VFIO to realize the subchannels passthrough, implement a vfio based subchannels passthrough driver called "vfio-ccw". Support qemu parameters in the style of: "-device vfio-ccw,sysfsdev=$mdev_file_path,devno=xx.x.xxxx' Reviewed-by: Eric Auger Acked-by: Alex Williamson Signed-off-by: Xiao Feng Ren Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-8-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- default-configs/s390x-softmmu.mak | 1 + hw/vfio/Makefile.objs | 1 + hw/vfio/ccw.c | 187 ++++++++++++++++++++++++++++++ include/hw/vfio/vfio-common.h | 1 + 4 files changed, 190 insertions(+) create mode 100644 hw/vfio/ccw.c diff --git a/default-configs/s390x-softmmu.mak b/default-configs/s390x-softmmu.mak index 9615a48f80..18aed56fc0 100644 --- a/default-configs/s390x-softmmu.mak +++ b/default-configs/s390x-softmmu.mak @@ -5,4 +5,5 @@ CONFIG_SCLPCONSOLE=y CONFIG_TERMINAL3270=y CONFIG_S390_FLIC=y CONFIG_S390_FLIC_KVM=$(CONFIG_KVM) +CONFIG_VFIO_CCW=$(CONFIG_LINUX) CONFIG_WDT_DIAG288=y diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index 05e7fbb93f..c3ab9097f1 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -1,6 +1,7 @@ ifeq ($(CONFIG_LINUX), y) obj-$(CONFIG_SOFTMMU) += common.o obj-$(CONFIG_PCI) += pci.o pci-quirks.o +obj-$(CONFIG_VFIO_CCW) += ccw.o obj-$(CONFIG_SOFTMMU) += platform.o obj-$(CONFIG_VFIO_XGMAC) += calxeda-xgmac.o obj-$(CONFIG_VFIO_AMD_XGBE) += amd-xgbe.o diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c new file mode 100644 index 0000000000..7d2497cee6 --- /dev/null +++ b/hw/vfio/ccw.c @@ -0,0 +1,187 @@ +/* + * vfio based subchannel assignment support + * + * Copyright 2017 IBM Corp. + * Author(s): Dong Jia Shi + * Xiao Feng Ren + * Pierre Morel + * + * This work is licensed under the terms of the GNU GPL, version 2 or(at + * your option) any version. See the COPYING file in the top-level + * directory. + */ + +#include +#include + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/sysbus.h" +#include "hw/vfio/vfio.h" +#include "hw/vfio/vfio-common.h" +#include "hw/s390x/s390-ccw.h" +#include "hw/s390x/ccw-device.h" + +#define TYPE_VFIO_CCW "vfio-ccw" +typedef struct VFIOCCWDevice { + S390CCWDevice cdev; + VFIODevice vdev; +} VFIOCCWDevice; + +static void vfio_ccw_compute_needs_reset(VFIODevice *vdev) +{ + vdev->needs_reset = false; +} + +/* + * We don't need vfio_hot_reset_multi and vfio_eoi operations for + * vfio_ccw device now. + */ +struct VFIODeviceOps vfio_ccw_ops = { + .vfio_compute_needs_reset = vfio_ccw_compute_needs_reset, +}; + +static void vfio_ccw_reset(DeviceState *dev) +{ + CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev); + S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev); + VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev); + + ioctl(vcdev->vdev.fd, VFIO_DEVICE_RESET); +} + +static void vfio_put_device(VFIOCCWDevice *vcdev) +{ + g_free(vcdev->vdev.name); + vfio_put_base_device(&vcdev->vdev); +} + +static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) +{ + char *tmp, group_path[PATH_MAX]; + ssize_t len; + int groupid; + + tmp = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/%s/iommu_group", + cdev->hostid.cssid, cdev->hostid.ssid, + cdev->hostid.devid, cdev->mdevid); + len = readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <= 0 || len >= sizeof(group_path)) { + error_setg(errp, "vfio: no iommu_group found"); + return NULL; + } + + group_path[len] = 0; + + if (sscanf(basename(group_path), "%d", &groupid) != 1) { + error_setg(errp, "vfio: failed to read %s", group_path); + return NULL; + } + + return vfio_get_group(groupid, &address_space_memory, errp); +} + +static void vfio_ccw_realize(DeviceState *dev, Error **errp) +{ + VFIODevice *vbasedev; + VFIOGroup *group; + CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev); + S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev); + VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev); + S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); + Error *err = NULL; + + /* Call the class init function for subchannel. */ + if (cdc->realize) { + cdc->realize(cdev, vcdev->vdev.sysfsdev, &err); + if (err) { + goto out_err_propagate; + } + } + + group = vfio_ccw_get_group(cdev, &err); + if (!group) { + goto out_group_err; + } + + vcdev->vdev.ops = &vfio_ccw_ops; + vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW; + vcdev->vdev.name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid, + cdev->hostid.ssid, cdev->hostid.devid); + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (strcmp(vbasedev->name, vcdev->vdev.name) == 0) { + error_setg(&err, "vfio: subchannel %s has already been attached", + vcdev->vdev.name); + goto out_device_err; + } + } + + if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, &err)) { + goto out_device_err; + } + + return; + +out_device_err: + vfio_put_group(group); +out_group_err: + if (cdc->unrealize) { + cdc->unrealize(cdev, NULL); + } +out_err_propagate: + error_propagate(errp, err); +} + +static void vfio_ccw_unrealize(DeviceState *dev, Error **errp) +{ + CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev); + S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev); + VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev); + S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); + VFIOGroup *group = vcdev->vdev.group; + + vfio_put_device(vcdev); + vfio_put_group(group); + + if (cdc->unrealize) { + cdc->unrealize(cdev, errp); + } +} + +static Property vfio_ccw_properties[] = { + DEFINE_PROP_STRING("sysfsdev", VFIOCCWDevice, vdev.sysfsdev), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vfio_ccw_vmstate = { + .name = TYPE_VFIO_CCW, + .unmigratable = 1, +}; + +static void vfio_ccw_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->props = vfio_ccw_properties; + dc->vmsd = &vfio_ccw_vmstate; + dc->desc = "VFIO-based subchannel assignment"; + dc->realize = vfio_ccw_realize; + dc->unrealize = vfio_ccw_unrealize; + dc->reset = vfio_ccw_reset; +} + +static const TypeInfo vfio_ccw_info = { + .name = TYPE_VFIO_CCW, + .parent = TYPE_S390_CCW, + .instance_size = sizeof(VFIOCCWDevice), + .class_init = vfio_ccw_class_init, +}; + +static void register_vfio_ccw_type(void) +{ + type_register_static(&vfio_ccw_info); +} + +type_init(register_vfio_ccw_type) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c582de18c9..9521013d52 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -45,6 +45,7 @@ enum { VFIO_DEVICE_TYPE_PCI = 0, VFIO_DEVICE_TYPE_PLATFORM = 1, + VFIO_DEVICE_TYPE_CCW = 2, }; typedef struct VFIOMmap { From c14e706ce9a4354c803e8f64bd12148831f888a3 Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:08 +0200 Subject: [PATCH 15/21] vfio/ccw: get io region info vfio-ccw provides an MMIO region for I/O operations. We fetch its information via ioctls here, then we can use it performing I/O instructions and retrieving I/O results later on. Reviewed-by: Eric Auger Acked-by: Alex Williamson Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-9-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/vfio/ccw.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 7d2497cee6..7ddcfd7767 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -12,6 +12,7 @@ */ #include +#include #include #include "qemu/osdep.h" @@ -26,6 +27,9 @@ typedef struct VFIOCCWDevice { S390CCWDevice cdev; VFIODevice vdev; + uint64_t io_region_size; + uint64_t io_region_offset; + struct ccw_io_region *io_region; } VFIOCCWDevice; static void vfio_ccw_compute_needs_reset(VFIODevice *vdev) @@ -50,6 +54,48 @@ static void vfio_ccw_reset(DeviceState *dev) ioctl(vcdev->vdev.fd, VFIO_DEVICE_RESET); } +static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) +{ + VFIODevice *vdev = &vcdev->vdev; + struct vfio_region_info *info; + int ret; + + /* Sanity check device */ + if (!(vdev->flags & VFIO_DEVICE_FLAGS_CCW)) { + error_setg(errp, "vfio: Um, this isn't a vfio-ccw device"); + return; + } + + if (vdev->num_regions < VFIO_CCW_CONFIG_REGION_INDEX + 1) { + error_setg(errp, "vfio: Unexpected number of the I/O region %u", + vdev->num_regions); + return; + } + + ret = vfio_get_region_info(vdev, VFIO_CCW_CONFIG_REGION_INDEX, &info); + if (ret) { + error_setg_errno(errp, -ret, "vfio: Error getting config info"); + return; + } + + vcdev->io_region_size = info->size; + if (sizeof(*vcdev->io_region) != vcdev->io_region_size) { + error_setg(errp, "vfio: Unexpected size of the I/O region"); + g_free(info); + return; + } + + vcdev->io_region_offset = info->offset; + vcdev->io_region = g_malloc0(info->size); + + g_free(info); +} + +static void vfio_ccw_put_region(VFIOCCWDevice *vcdev) +{ + g_free(vcdev->io_region); +} + static void vfio_put_device(VFIOCCWDevice *vcdev) { g_free(vcdev->vdev.name); @@ -122,8 +168,15 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) goto out_device_err; } + vfio_ccw_get_region(vcdev, &err); + if (err) { + goto out_region_err; + } + return; +out_region_err: + vfio_put_device(vcdev); out_device_err: vfio_put_group(group); out_group_err: @@ -142,6 +195,7 @@ static void vfio_ccw_unrealize(DeviceState *dev, Error **errp) S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); VFIOGroup *group = vcdev->vdev.group; + vfio_ccw_put_region(vcdev); vfio_put_device(vcdev); vfio_put_group(group); From 4886b3e9f00683324c0368b1dec8acb964f4a439 Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:09 +0200 Subject: [PATCH 16/21] vfio/ccw: get irqs info and set the eventfd fd vfio-ccw resorts to the eventfd mechanism to communicate with userspace. We fetch the irqs info via the ioctl VFIO_DEVICE_GET_IRQ_INFO, register a event notifier to get the eventfd fd which is sent to kernel via the ioctl VFIO_DEVICE_SET_IRQS, then we can implement read operation once kernel sends the signal. Reviewed-by: Eric Auger Acked-by: Alex Williamson Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-10-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/vfio/ccw.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 7ddcfd7767..689a7724b6 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -22,6 +22,7 @@ #include "hw/vfio/vfio-common.h" #include "hw/s390x/s390-ccw.h" #include "hw/s390x/ccw-device.h" +#include "qemu/error-report.h" #define TYPE_VFIO_CCW "vfio-ccw" typedef struct VFIOCCWDevice { @@ -30,6 +31,7 @@ typedef struct VFIOCCWDevice { uint64_t io_region_size; uint64_t io_region_offset; struct ccw_io_region *io_region; + EventNotifier io_notifier; } VFIOCCWDevice; static void vfio_ccw_compute_needs_reset(VFIODevice *vdev) @@ -54,6 +56,97 @@ static void vfio_ccw_reset(DeviceState *dev) ioctl(vcdev->vdev.fd, VFIO_DEVICE_RESET); } +static void vfio_ccw_io_notifier_handler(void *opaque) +{ + VFIOCCWDevice *vcdev = opaque; + + if (!event_notifier_test_and_clear(&vcdev->io_notifier)) { + return; + } +} + +static void vfio_ccw_register_io_notifier(VFIOCCWDevice *vcdev, Error **errp) +{ + VFIODevice *vdev = &vcdev->vdev; + struct vfio_irq_info *irq_info; + struct vfio_irq_set *irq_set; + size_t argsz; + int32_t *pfd; + + if (vdev->num_irqs < VFIO_CCW_IO_IRQ_INDEX + 1) { + error_setg(errp, "vfio: unexpected number of io irqs %u", + vdev->num_irqs); + return; + } + + argsz = sizeof(*irq_set); + irq_info = g_malloc0(argsz); + irq_info->index = VFIO_CCW_IO_IRQ_INDEX; + irq_info->argsz = argsz; + if (ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, + irq_info) < 0 || irq_info->count < 1) { + error_setg_errno(errp, errno, "vfio: Error getting irq info"); + goto out_free_info; + } + + if (event_notifier_init(&vcdev->io_notifier, 0)) { + error_setg_errno(errp, errno, + "vfio: Unable to init event notifier for IO"); + goto out_free_info; + } + + argsz = sizeof(*irq_set) + sizeof(*pfd); + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_CCW_IO_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *) &irq_set->data; + + *pfd = event_notifier_get_fd(&vcdev->io_notifier); + qemu_set_fd_handler(*pfd, vfio_ccw_io_notifier_handler, NULL, vcdev); + if (ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + error_setg(errp, "vfio: Failed to set up io notification"); + qemu_set_fd_handler(*pfd, NULL, NULL, vcdev); + event_notifier_cleanup(&vcdev->io_notifier); + } + + g_free(irq_set); + +out_free_info: + g_free(irq_info); +} + +static void vfio_ccw_unregister_io_notifier(VFIOCCWDevice *vcdev) +{ + struct vfio_irq_set *irq_set; + size_t argsz; + int32_t *pfd; + + argsz = sizeof(*irq_set) + sizeof(*pfd); + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_CCW_IO_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *) &irq_set->data; + *pfd = -1; + + if (ioctl(vcdev->vdev.fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + error_report("vfio: Failed to de-assign device io fd: %m"); + } + + qemu_set_fd_handler(event_notifier_get_fd(&vcdev->io_notifier), + NULL, NULL, vcdev); + event_notifier_cleanup(&vcdev->io_notifier); + + g_free(irq_set); +} + static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) { VFIODevice *vdev = &vcdev->vdev; @@ -173,8 +266,15 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) goto out_region_err; } + vfio_ccw_register_io_notifier(vcdev, &err); + if (err) { + goto out_notifier_err; + } + return; +out_notifier_err: + vfio_ccw_put_region(vcdev); out_region_err: vfio_put_device(vcdev); out_device_err: @@ -195,6 +295,7 @@ static void vfio_ccw_unrealize(DeviceState *dev, Error **errp) S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); VFIOGroup *group = vcdev->vdev.group; + vfio_ccw_unregister_io_notifier(vcdev); vfio_ccw_put_region(vcdev); vfio_put_device(vcdev); vfio_put_group(group); From 8ca2b376b47fff58f7ab6f16d86a66d4af3a2be2 Mon Sep 17 00:00:00 2001 From: Xiao Feng Ren Date: Wed, 17 May 2017 02:48:10 +0200 Subject: [PATCH 17/21] s390x/css: introduce and realize ccw-request callback Introduce a new callback on subchannel to handle ccw-request. Realize the callback in vfio-ccw device. Besides, resort to the event notifier handler to handling the ccw-request results. 1. Pread the I/O results via MMIO region. 2. Update the scsw info to guest. 3. Inject an I/O interrupt to notify guest the I/O result. Acked-by: Alex Williamson Signed-off-by: Xiao Feng Ren Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-11-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/css.c | 4 +- hw/vfio/ccw.c | 85 +++++++++++++++++++++++++++++++++++++ include/hw/s390x/css.h | 2 + include/hw/s390x/s390-ccw.h | 1 + 4 files changed, 90 insertions(+), 2 deletions(-) diff --git a/hw/s390x/css.c b/hw/s390x/css.c index a8aed9cb3a..462a768f9e 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -259,7 +259,7 @@ uint16_t css_build_subchannel_id(SubchDev *sch) return css_do_build_subchannel_id(sch->cssid, sch->ssid); } -static void css_inject_io_interrupt(SubchDev *sch) +void css_inject_io_interrupt(SubchDev *sch) { uint8_t isc = (sch->curr_status.pmcw.flags & PMCW_FLAGS_MASK_ISC) >> 11; @@ -671,7 +671,7 @@ static void copy_pmcw_to_guest(PMCW *dest, const PMCW *src) dest->chars = cpu_to_be32(src->chars); } -static void copy_scsw_to_guest(SCSW *dest, const SCSW *src) +void copy_scsw_to_guest(SCSW *dest, const SCSW *src) { dest->flags = cpu_to_be16(src->flags); dest->ctrl = cpu_to_be16(src->ctrl); diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 689a7724b6..007ce435f1 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -47,6 +47,36 @@ struct VFIODeviceOps vfio_ccw_ops = { .vfio_compute_needs_reset = vfio_ccw_compute_needs_reset, }; +static int vfio_ccw_handle_request(ORB *orb, SCSW *scsw, void *data) +{ + S390CCWDevice *cdev = data; + VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev); + struct ccw_io_region *region = vcdev->io_region; + int ret; + + QEMU_BUILD_BUG_ON(sizeof(region->orb_area) != sizeof(ORB)); + QEMU_BUILD_BUG_ON(sizeof(region->scsw_area) != sizeof(SCSW)); + QEMU_BUILD_BUG_ON(sizeof(region->irb_area) != sizeof(IRB)); + + memset(region, 0, sizeof(*region)); + + memcpy(region->orb_area, orb, sizeof(ORB)); + memcpy(region->scsw_area, scsw, sizeof(SCSW)); + +again: + ret = pwrite(vcdev->vdev.fd, region, + vcdev->io_region_size, vcdev->io_region_offset); + if (ret != vcdev->io_region_size) { + if (errno == EAGAIN) { + goto again; + } + error_report("vfio-ccw: wirte I/O region failed with errno=%d", errno); + return -errno; + } + + return region->ret_code; +} + static void vfio_ccw_reset(DeviceState *dev) { CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev); @@ -59,10 +89,62 @@ static void vfio_ccw_reset(DeviceState *dev) static void vfio_ccw_io_notifier_handler(void *opaque) { VFIOCCWDevice *vcdev = opaque; + struct ccw_io_region *region = vcdev->io_region; + S390CCWDevice *cdev = S390_CCW_DEVICE(vcdev); + CcwDevice *ccw_dev = CCW_DEVICE(cdev); + SubchDev *sch = ccw_dev->sch; + SCSW *s = &sch->curr_status.scsw; + IRB irb; + int size; if (!event_notifier_test_and_clear(&vcdev->io_notifier)) { return; } + + size = pread(vcdev->vdev.fd, region, vcdev->io_region_size, + vcdev->io_region_offset); + if (size == -1) { + switch (errno) { + case ENODEV: + /* Generate a deferred cc 3 condition. */ + s->flags |= SCSW_FLAGS_MASK_CC; + s->ctrl &= ~SCSW_CTRL_MASK_STCTL; + s->ctrl |= (SCSW_STCTL_ALERT | SCSW_STCTL_STATUS_PEND); + goto read_err; + case EFAULT: + /* Memory problem, generate channel data check. */ + s->ctrl &= ~SCSW_ACTL_START_PEND; + s->cstat = SCSW_CSTAT_DATA_CHECK; + s->ctrl &= ~SCSW_CTRL_MASK_STCTL; + s->ctrl |= SCSW_STCTL_PRIMARY | SCSW_STCTL_SECONDARY | + SCSW_STCTL_ALERT | SCSW_STCTL_STATUS_PEND; + goto read_err; + default: + /* Error, generate channel program check. */ + s->ctrl &= ~SCSW_ACTL_START_PEND; + s->cstat = SCSW_CSTAT_PROG_CHECK; + s->ctrl &= ~SCSW_CTRL_MASK_STCTL; + s->ctrl |= SCSW_STCTL_PRIMARY | SCSW_STCTL_SECONDARY | + SCSW_STCTL_ALERT | SCSW_STCTL_STATUS_PEND; + goto read_err; + } + } else if (size != vcdev->io_region_size) { + /* Information transfer error, generate channel-control check. */ + s->ctrl &= ~SCSW_ACTL_START_PEND; + s->cstat = SCSW_CSTAT_CHN_CTRL_CHK; + s->ctrl &= ~SCSW_CTRL_MASK_STCTL; + s->ctrl |= SCSW_STCTL_PRIMARY | SCSW_STCTL_SECONDARY | + SCSW_STCTL_ALERT | SCSW_STCTL_STATUS_PEND; + goto read_err; + } + + memcpy(&irb, region->irb_area, sizeof(IRB)); + + /* Update control block via irb. */ + copy_scsw_to_guest(s, &irb.scsw); + +read_err: + css_inject_io_interrupt(sch); } static void vfio_ccw_register_io_notifier(VFIOCCWDevice *vcdev, Error **errp) @@ -318,6 +400,7 @@ static const VMStateDescription vfio_ccw_vmstate = { static void vfio_ccw_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + S390CCWDeviceClass *cdc = S390_CCW_DEVICE_CLASS(klass); dc->props = vfio_ccw_properties; dc->vmsd = &vfio_ccw_vmstate; @@ -325,6 +408,8 @@ static void vfio_ccw_class_init(ObjectClass *klass, void *data) dc->realize = vfio_ccw_realize; dc->unrealize = vfio_ccw_unrealize; dc->reset = vfio_ccw_reset; + + cdc->handle_request = vfio_ccw_handle_request; } static const TypeInfo vfio_ccw_info = { diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index 60ff83e9c1..a932f91edb 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -137,6 +137,8 @@ void css_sch_build_virtual_schib(SubchDev *sch, uint8_t chpid, uint8_t type); int css_sch_build_schib(SubchDev *sch, CssDevId *dev_id); unsigned int css_find_free_chpid(uint8_t cssid); uint16_t css_build_subchannel_id(SubchDev *sch); +void copy_scsw_to_guest(SCSW *dest, const SCSW *src); +void css_inject_io_interrupt(SubchDev *sch); void css_reset(void); void css_reset_sch(SubchDev *sch); void css_queue_crw(uint8_t rsc, uint8_t erc, int chain, uint16_t rsid); diff --git a/include/hw/s390x/s390-ccw.h b/include/hw/s390x/s390-ccw.h index b58d8e9ca3..9f45cf1347 100644 --- a/include/hw/s390x/s390-ccw.h +++ b/include/hw/s390x/s390-ccw.h @@ -33,6 +33,7 @@ typedef struct S390CCWDeviceClass { CCWDeviceClass parent_class; void (*realize)(S390CCWDevice *dev, char *sysfsdev, Error **errp); void (*unrealize)(S390CCWDevice *dev, Error **errp); + int (*handle_request) (ORB *, SCSW *, void *); } S390CCWDeviceClass; #endif From bab482d7405f9fe3cac9c213d60f9ca9442c047b Mon Sep 17 00:00:00 2001 From: Xiao Feng Ren Date: Wed, 17 May 2017 02:48:11 +0200 Subject: [PATCH 18/21] s390x/css: ccw translation infrastructure Implement a basic infrastructure of handling channel I/O instruction interception for passed through subchannels: 1. Branch the code path of instruction interception handling by SubChannel type. 2. For a passed-through subchannel, issue the ORB to kernel to do ccw translation and perform an I/O operation. 3. Assign different condition code based on the I/O result, or trigger a program check. Signed-off-by: Xiao Feng Ren Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-12-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/css.c | 89 +++++++++++++++++++++++++++++++++++++++--- hw/s390x/s390-ccw.c | 12 ++++++ hw/s390x/virtio-ccw.c | 1 + include/hw/s390x/css.h | 4 ++ target/s390x/ioinst.c | 9 +++++ 5 files changed, 109 insertions(+), 6 deletions(-) diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 462a768f9e..1e2f26b65a 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -524,7 +524,7 @@ static int css_interpret_ccw(SubchDev *sch, hwaddr ccw_addr, return ret; } -static void sch_handle_start_func(SubchDev *sch, ORB *orb) +static void sch_handle_start_func_virtual(SubchDev *sch, ORB *orb) { PMCW *p = &sch->curr_status.pmcw; @@ -626,13 +626,58 @@ static void sch_handle_start_func(SubchDev *sch, ORB *orb) } +static int sch_handle_start_func_passthrough(SubchDev *sch, ORB *orb) +{ + + PMCW *p = &sch->curr_status.pmcw; + SCSW *s = &sch->curr_status.scsw; + int ret; + + if (!(s->ctrl & SCSW_ACTL_SUSP)) { + assert(orb != NULL); + p->intparm = orb->intparm; + } + + /* + * Only support prefetch enable mode. + * Only support 64bit addressing idal. + */ + if (!(orb->ctrl0 & ORB_CTRL0_MASK_PFCH) || + !(orb->ctrl0 & ORB_CTRL0_MASK_C64)) { + return -EINVAL; + } + + ret = s390_ccw_cmd_request(orb, s, sch->driver_data); + switch (ret) { + /* Currently we don't update control block and just return the cc code. */ + case 0: + break; + case -EBUSY: + break; + case -ENODEV: + break; + case -EACCES: + /* Let's reflect an inaccessible host device by cc 3. */ + ret = -ENODEV; + break; + default: + /* + * All other return codes will trigger a program check, + * or set cc to 1. + */ + break; + }; + + return ret; +} + /* * On real machines, this would run asynchronously to the main vcpus. * We might want to make some parts of the ssch handling (interpreting * read/writes) asynchronous later on if we start supporting more than * our current very simple devices. */ -static void do_subchannel_work(SubchDev *sch, ORB *orb) +int do_subchannel_work_virtual(SubchDev *sch, ORB *orb) { SCSW *s = &sch->curr_status.scsw; @@ -643,12 +688,45 @@ static void do_subchannel_work(SubchDev *sch, ORB *orb) sch_handle_halt_func(sch); } else if (s->ctrl & SCSW_FCTL_START_FUNC) { /* Triggered by both ssch and rsch. */ - sch_handle_start_func(sch, orb); + sch_handle_start_func_virtual(sch, orb); } else { /* Cannot happen. */ - return; + return 0; } css_inject_io_interrupt(sch); + return 0; +} + +int do_subchannel_work_passthrough(SubchDev *sch, ORB *orb) +{ + int ret; + SCSW *s = &sch->curr_status.scsw; + + if (s->ctrl & SCSW_FCTL_CLEAR_FUNC) { + /* TODO: Clear handling */ + sch_handle_clear_func(sch); + ret = 0; + } else if (s->ctrl & SCSW_FCTL_HALT_FUNC) { + /* TODO: Halt handling */ + sch_handle_halt_func(sch); + ret = 0; + } else if (s->ctrl & SCSW_FCTL_START_FUNC) { + ret = sch_handle_start_func_passthrough(sch, orb); + } else { + /* Cannot happen. */ + return -ENODEV; + } + + return ret; +} + +static int do_subchannel_work(SubchDev *sch, ORB *orb) +{ + if (sch->do_subchannel_work) { + return sch->do_subchannel_work(sch, orb); + } else { + return -EINVAL; + } } static void copy_pmcw_to_guest(PMCW *dest, const PMCW *src) @@ -967,8 +1045,7 @@ int css_do_ssch(SubchDev *sch, ORB *orb) s->ctrl |= (SCSW_FCTL_START_FUNC | SCSW_ACTL_START_PEND); s->flags &= ~SCSW_FLAGS_MASK_PNO; - do_subchannel_work(sch, orb); - ret = 0; + ret = do_subchannel_work(sch, orb); out: return ret; diff --git a/hw/s390x/s390-ccw.c b/hw/s390x/s390-ccw.c index e2b1973fda..8614dda6f8 100644 --- a/hw/s390x/s390-ccw.c +++ b/hw/s390x/s390-ccw.c @@ -18,6 +18,17 @@ #include "hw/s390x/css-bridge.h" #include "hw/s390x/s390-ccw.h" +int s390_ccw_cmd_request(ORB *orb, SCSW *scsw, void *data) +{ + S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(data); + + if (cdc->handle_request) { + return cdc->handle_request(orb, scsw, data); + } else { + return -ENOSYS; + } +} + static void s390_ccw_get_dev_info(S390CCWDevice *cdev, char *sysfsdev, Error **errp) @@ -72,6 +83,7 @@ static void s390_ccw_realize(S390CCWDevice *cdev, char *sysfsdev, Error **errp) goto out_mdevid_free; } sch->driver_data = cdev; + sch->do_subchannel_work = do_subchannel_work_passthrough; ccw_dev->sch = sch; ret = css_sch_build_schib(sch, &cdev->hostid); diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index 4e386e9781..e6a6f74be3 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -701,6 +701,7 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp) sch->disable_cb = virtio_sch_disable_cb; sch->id.reserved = 0xff; sch->id.cu_type = VIRTIO_CCW_CU_TYPE; + sch->do_subchannel_work = do_subchannel_work_virtual; ccw_dev->sch = sch; dev->indicators = NULL; dev->revision = -1; diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index a932f91edb..596a2f2ef3 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -91,6 +91,7 @@ struct SubchDev { /* transport-provided data: */ int (*ccw_cb) (SubchDev *, CCW1); void (*disable_cb)(SubchDev *); + int (*do_subchannel_work) (SubchDev *, ORB *); SenseId id; void *driver_data; }; @@ -148,6 +149,9 @@ void css_generate_chp_crws(uint8_t cssid, uint8_t chpid); void css_generate_css_crws(uint8_t cssid); void css_clear_sei_pending(void); void css_adapter_interrupt(uint8_t isc); +int s390_ccw_cmd_request(ORB *orb, SCSW *scsw, void *data); +int do_subchannel_work_virtual(SubchDev *sub, ORB *orb); +int do_subchannel_work_passthrough(SubchDev *sub, ORB *orb); typedef enum { CSS_IO_ADAPTER_VIRTIO = 0, diff --git a/target/s390x/ioinst.c b/target/s390x/ioinst.c index 590bfa4f12..62a777100c 100644 --- a/target/s390x/ioinst.c +++ b/target/s390x/ioinst.c @@ -244,6 +244,15 @@ void ioinst_handle_ssch(S390CPU *cpu, uint64_t reg1, uint32_t ipb) case -EBUSY: cc = 2; break; + case -EFAULT: + /* + * TODO: + * I'm wondering whether there is something better + * to do for us here (like setting some device or + * subchannel status). + */ + program_interrupt(env, PGM_ADDRESSING, 4); + return; case 0: cc = 0; break; From 334e76850bbbdc977656cc8a77ce101af00ba13d Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:12 +0200 Subject: [PATCH 19/21] vfio/ccw: update sense data if a unit check is pending Concurrent-sense data is currently not delivered. This patch stores the concurrent-sense data to the subchannel if a unit check is pending and the concurrent-sense bit is enabled. Then a TSCH can retreive the right IRB data back to the guest. Acked-by: Alex Williamson Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-13-bjsdjshi@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck --- hw/vfio/ccw.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 007ce435f1..12d0262336 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -94,6 +94,7 @@ static void vfio_ccw_io_notifier_handler(void *opaque) CcwDevice *ccw_dev = CCW_DEVICE(cdev); SubchDev *sch = ccw_dev->sch; SCSW *s = &sch->curr_status.scsw; + PMCW *p = &sch->curr_status.pmcw; IRB irb; int size; @@ -143,6 +144,12 @@ static void vfio_ccw_io_notifier_handler(void *opaque) /* Update control block via irb. */ copy_scsw_to_guest(s, &irb.scsw); + /* If a uint check is pending, copy sense data. */ + if ((s->dstat & SCSW_DSTAT_UNIT_CHECK) && + (p->chars & PMCW_CHARS_MASK_CSENSE)) { + memcpy(sch->sense_data, irb.ecw, sizeof(irb.ecw)); + } + read_err: css_inject_io_interrupt(sch); } From 5eb74557cdbac602117fa2d30e08a76b82fb0301 Mon Sep 17 00:00:00 2001 From: Dong Jia Shi Date: Wed, 17 May 2017 02:48:13 +0200 Subject: [PATCH 20/21] MAINTAINERS: Add vfio-ccw maintainer Add Cornelia Huck as the vfio-ccw maintainer. Acked-by: Alex Williamson Signed-off-by: Dong Jia Shi Message-Id: <20170517004813.58227-14-bjsdjshi@linux.vnet.ibm.com> [CH: add tree] Signed-off-by: Cornelia Huck --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ef2ec58a94..7df088259b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1005,6 +1005,14 @@ S: Supported F: hw/vfio/* F: include/hw/vfio/ +vfio-ccw +M: Cornelia Huck +S: Supported +F: hw/vfio/ccw.c +F: hw/s390x/s390-ccw.c +F: include/hw/s390x/s390-ccw.h +T: git git://github.com/cohuck/qemu.git s390-next + vhost M: Michael S. Tsirkin S: Supported From cb4f4bc3535f554daa3266aaa447843949a68193 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 12 May 2017 13:47:30 +0200 Subject: [PATCH 21/21] s390/kvm: do not reset riccb on initial cpu reset The riccb is kept unchanged during initial cpu reset. Move the data structure to the other registers that are unchanged. Signed-off-by: Christian Borntraeger Signed-off-by: Cornelia Huck --- target/s390x/cpu.c | 7 ++++--- target/s390x/cpu.h | 6 ++++-- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index a1bf2ba5a7..a69005d9b5 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -92,9 +92,10 @@ static void s390_cpu_initial_reset(CPUState *s) int i; s390_cpu_reset(s); - /* initial reset does not touch regs,fregs and aregs */ - memset(&env->fpc, 0, offsetof(CPUS390XState, end_reset_fields) - - offsetof(CPUS390XState, fpc)); + /* initial reset does not clear everything! */ + memset(&env->start_initial_reset_fields, 0, + offsetof(CPUS390XState, end_reset_fields) - + offsetof(CPUS390XState, start_initial_reset_fields)); /* architectured initial values for CR 0 and 14 */ env->cregs[0] = CR0_RESET; diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index e27d9d874a..c74b4193ee 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -88,6 +88,10 @@ typedef struct CPUS390XState { */ CPU_DoubleU vregs[32][2]; /* vector registers */ uint32_t aregs[16]; /* access registers */ + uint8_t riccb[64]; /* runtime instrumentation control */ + + /* Fields up to this point are not cleared by initial CPU reset */ + struct {} start_initial_reset_fields; uint32_t fpc; /* floating-point control register */ uint32_t cc_op; @@ -137,8 +141,6 @@ typedef struct CPUS390XState { uint64_t gbea; uint64_t pp; - uint8_t riccb[64]; - /* Fields up to this point are cleared by a CPU reset */ struct {} end_reset_fields;