Xen-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Roger Pau Monne <roger.pau@citrix.com>
To: <xen-devel@lists.xenproject.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>, Wei Liu <wl@xen.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	George Dunlap <George.Dunlap@eu.citrix.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>, Tim Deegan <tim@xen.org>,
	Julien Grall <julien.grall@arm.com>,
	Paul Durrant <paul.durrant@citrix.com>,
	Jan Beulich <jbeulich@suse.com>,
	Roger Pau Monne <roger.pau@citrix.com>
Subject: [Xen-devel] [PATCH 6/7] vpci: register as an internal ioreq server
Date: Wed, 21 Aug 2019 16:59:02 +0200
Message-ID: <20190821145903.45934-7-roger.pau@citrix.com> (raw)
In-Reply-To: <20190821145903.45934-1-roger.pau@citrix.com>

Switch vPCI to become an internal ioreq server, and hence drop all the
vPCI specific decoding and trapping to PCI IO ports and MMCFG regions.

This allows to unify the vPCI code with the ioreq infrastructure,
opening the door for domains having PCI accesses handled by vPCI and
other ioreq servers at the same time.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
---
 xen/arch/x86/hvm/dom0_build.c       |   9 +-
 xen/arch/x86/hvm/hvm.c              |   5 +-
 xen/arch/x86/hvm/io.c               | 272 ----------------------------
 xen/arch/x86/hvm/ioreq.c            |   5 +
 xen/arch/x86/physdev.c              |   7 +-
 xen/drivers/passthrough/x86/iommu.c |   2 +-
 xen/drivers/vpci/vpci.c             |  54 ++++++
 xen/include/asm-x86/hvm/io.h        |   2 +-
 xen/include/xen/vpci.h              |   3 +
 9 files changed, 77 insertions(+), 282 deletions(-)

diff --git a/xen/arch/x86/hvm/dom0_build.c b/xen/arch/x86/hvm/dom0_build.c
index 8845399ae9..7925189fed 100644
--- a/xen/arch/x86/hvm/dom0_build.c
+++ b/xen/arch/x86/hvm/dom0_build.c
@@ -29,6 +29,7 @@
 
 #include <asm/bzimage.h>
 #include <asm/dom0_build.h>
+#include <asm/hvm/ioreq.h>
 #include <asm/hvm/support.h>
 #include <asm/io_apic.h>
 #include <asm/p2m.h>
@@ -1117,10 +1118,10 @@ static void __hwdom_init pvh_setup_mmcfg(struct domain *d)
 
     for ( i = 0; i < pci_mmcfg_config_num; i++ )
     {
-        rc = register_vpci_mmcfg_handler(d, pci_mmcfg_config[i].address,
-                                         pci_mmcfg_config[i].start_bus_number,
-                                         pci_mmcfg_config[i].end_bus_number,
-                                         pci_mmcfg_config[i].pci_segment);
+        rc = hvm_ioreq_register_mmcfg(d, pci_mmcfg_config[i].address,
+                                      pci_mmcfg_config[i].start_bus_number,
+                                      pci_mmcfg_config[i].end_bus_number,
+                                      pci_mmcfg_config[i].pci_segment);
         if ( rc )
             printk("Unable to setup MMCFG handler at %#lx for segment %u\n",
                    pci_mmcfg_config[i].address,
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index b7a53377a5..3fcf46779b 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -644,10 +644,13 @@ int hvm_domain_initialise(struct domain *d)
         d->arch.hvm.io_bitmap = hvm_io_bitmap;
 
     register_g2m_portio_handler(d);
-    register_vpci_portio_handler(d);
 
     hvm_ioreq_init(d);
 
+    rc = vpci_register_ioreq(d);
+    if ( rc )
+        goto fail1;
+
     hvm_init_guest_time(d);
 
     d->arch.hvm.params[HVM_PARAM_TRIPLE_FAULT_REASON] = SHUTDOWN_reboot;
diff --git a/xen/arch/x86/hvm/io.c b/xen/arch/x86/hvm/io.c
index 6585767c03..9c323d17ef 100644
--- a/xen/arch/x86/hvm/io.c
+++ b/xen/arch/x86/hvm/io.c
@@ -290,278 +290,6 @@ unsigned int hvm_mmcfg_decode_addr(const struct hvm_mmcfg *mmcfg,
     return addr & (PCI_CFG_SPACE_EXP_SIZE - 1);
 }
 
-
-/* Do some sanity checks. */
-static bool vpci_access_allowed(unsigned int reg, unsigned int len)
-{
-    /* Check access size. */
-    if ( len != 1 && len != 2 && len != 4 && len != 8 )
-        return false;
-
-    /* Check that access is size aligned. */
-    if ( (reg & (len - 1)) )
-        return false;
-
-    return true;
-}
-
-/* vPCI config space IO ports handlers (0xcf8/0xcfc). */
-static bool vpci_portio_accept(const struct hvm_io_handler *handler,
-                               const ioreq_t *p)
-{
-    return (p->addr == 0xcf8 && p->size == 4) || (p->addr & ~3) == 0xcfc;
-}
-
-static int vpci_portio_read(const struct hvm_io_handler *handler,
-                            uint64_t addr, uint32_t size, uint64_t *data)
-{
-    const struct domain *d = current->domain;
-    unsigned int reg;
-    pci_sbdf_t sbdf;
-    uint32_t cf8;
-
-    *data = ~(uint64_t)0;
-
-    if ( addr == 0xcf8 )
-    {
-        ASSERT(size == 4);
-        *data = d->arch.hvm.pci_cf8;
-        return X86EMUL_OKAY;
-    }
-
-    ASSERT((addr & ~3) == 0xcfc);
-    cf8 = ACCESS_ONCE(d->arch.hvm.pci_cf8);
-    if ( !CF8_ENABLED(cf8) )
-        return X86EMUL_UNHANDLEABLE;
-
-    reg = hvm_pci_decode_addr(cf8, addr, &sbdf);
-
-    if ( !vpci_access_allowed(reg, size) )
-        return X86EMUL_OKAY;
-
-    *data = vpci_read(sbdf, reg, size);
-
-    return X86EMUL_OKAY;
-}
-
-static int vpci_portio_write(const struct hvm_io_handler *handler,
-                             uint64_t addr, uint32_t size, uint64_t data)
-{
-    struct domain *d = current->domain;
-    unsigned int reg;
-    pci_sbdf_t sbdf;
-    uint32_t cf8;
-
-    if ( addr == 0xcf8 )
-    {
-        ASSERT(size == 4);
-        d->arch.hvm.pci_cf8 = data;
-        return X86EMUL_OKAY;
-    }
-
-    ASSERT((addr & ~3) == 0xcfc);
-    cf8 = ACCESS_ONCE(d->arch.hvm.pci_cf8);
-    if ( !CF8_ENABLED(cf8) )
-        return X86EMUL_UNHANDLEABLE;
-
-    reg = hvm_pci_decode_addr(cf8, addr, &sbdf);
-
-    if ( !vpci_access_allowed(reg, size) )
-        return X86EMUL_OKAY;
-
-    vpci_write(sbdf, reg, size, data);
-
-    return X86EMUL_OKAY;
-}
-
-static const struct hvm_io_ops vpci_portio_ops = {
-    .accept = vpci_portio_accept,
-    .read = vpci_portio_read,
-    .write = vpci_portio_write,
-};
-
-void register_vpci_portio_handler(struct domain *d)
-{
-    struct hvm_io_handler *handler;
-
-    if ( !has_vpci(d) )
-        return;
-
-    handler = hvm_next_io_handler(d);
-    if ( !handler )
-        return;
-
-    handler->type = IOREQ_TYPE_PIO;
-    handler->ops = &vpci_portio_ops;
-}
-
-/* Handlers to trap PCI MMCFG config accesses. */
-static const struct hvm_mmcfg *vpci_mmcfg_find(const struct domain *d,
-                                               paddr_t addr)
-{
-    const struct hvm_mmcfg *mmcfg;
-
-    list_for_each_entry ( mmcfg, &d->arch.hvm.mmcfg_regions, next )
-        if ( addr >= mmcfg->addr && addr < mmcfg->addr + mmcfg->size )
-            return mmcfg;
-
-    return NULL;
-}
-
-bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr)
-{
-    return vpci_mmcfg_find(d, addr);
-}
-
-static unsigned int vpci_mmcfg_decode_addr(const struct hvm_mmcfg *mmcfg,
-                                           paddr_t addr, pci_sbdf_t *sbdf)
-{
-    addr -= mmcfg->addr;
-    sbdf->bdf = MMCFG_BDF(addr);
-    sbdf->bus += mmcfg->start_bus;
-    sbdf->seg = mmcfg->segment;
-
-    return addr & (PCI_CFG_SPACE_EXP_SIZE - 1);
-}
-
-static int vpci_mmcfg_accept(struct vcpu *v, unsigned long addr)
-{
-    struct domain *d = v->domain;
-    bool found;
-
-    read_lock(&d->arch.hvm.mmcfg_lock);
-    found = vpci_mmcfg_find(d, addr);
-    read_unlock(&d->arch.hvm.mmcfg_lock);
-
-    return found;
-}
-
-static int vpci_mmcfg_read(struct vcpu *v, unsigned long addr,
-                           unsigned int len, unsigned long *data)
-{
-    struct domain *d = v->domain;
-    const struct hvm_mmcfg *mmcfg;
-    unsigned int reg;
-    pci_sbdf_t sbdf;
-
-    *data = ~0ul;
-
-    read_lock(&d->arch.hvm.mmcfg_lock);
-    mmcfg = vpci_mmcfg_find(d, addr);
-    if ( !mmcfg )
-    {
-        read_unlock(&d->arch.hvm.mmcfg_lock);
-        return X86EMUL_RETRY;
-    }
-
-    reg = vpci_mmcfg_decode_addr(mmcfg, addr, &sbdf);
-    read_unlock(&d->arch.hvm.mmcfg_lock);
-
-    if ( !vpci_access_allowed(reg, len) ||
-         (reg + len) > PCI_CFG_SPACE_EXP_SIZE )
-        return X86EMUL_OKAY;
-
-    /*
-     * According to the PCIe 3.1A specification:
-     *  - Configuration Reads and Writes must usually be DWORD or smaller
-     *    in size.
-     *  - Because Root Complex implementations are not required to support
-     *    accesses to a RCRB that cross DW boundaries [...] software
-     *    should take care not to cause the generation of such accesses
-     *    when accessing a RCRB unless the Root Complex will support the
-     *    access.
-     *  Xen however supports 8byte accesses by splitting them into two
-     *  4byte accesses.
-     */
-    *data = vpci_read(sbdf, reg, min(4u, len));
-    if ( len == 8 )
-        *data |= (uint64_t)vpci_read(sbdf, reg + 4, 4) << 32;
-
-    return X86EMUL_OKAY;
-}
-
-static int vpci_mmcfg_write(struct vcpu *v, unsigned long addr,
-                            unsigned int len, unsigned long data)
-{
-    struct domain *d = v->domain;
-    const struct hvm_mmcfg *mmcfg;
-    unsigned int reg;
-    pci_sbdf_t sbdf;
-
-    read_lock(&d->arch.hvm.mmcfg_lock);
-    mmcfg = vpci_mmcfg_find(d, addr);
-    if ( !mmcfg )
-    {
-        read_unlock(&d->arch.hvm.mmcfg_lock);
-        return X86EMUL_RETRY;
-    }
-
-    reg = vpci_mmcfg_decode_addr(mmcfg, addr, &sbdf);
-    read_unlock(&d->arch.hvm.mmcfg_lock);
-
-    if ( !vpci_access_allowed(reg, len) ||
-         (reg + len) > PCI_CFG_SPACE_EXP_SIZE )
-        return X86EMUL_OKAY;
-
-    vpci_write(sbdf, reg, min(4u, len), data);
-    if ( len == 8 )
-        vpci_write(sbdf, reg + 4, 4, data >> 32);
-
-    return X86EMUL_OKAY;
-}
-
-static const struct hvm_mmio_ops vpci_mmcfg_ops = {
-    .check = vpci_mmcfg_accept,
-    .read = vpci_mmcfg_read,
-    .write = vpci_mmcfg_write,
-};
-
-int register_vpci_mmcfg_handler(struct domain *d, paddr_t addr,
-                                unsigned int start_bus, unsigned int end_bus,
-                                unsigned int seg)
-{
-    struct hvm_mmcfg *mmcfg, *new;
-
-    ASSERT(is_hardware_domain(d));
-
-    if ( start_bus > end_bus )
-        return -EINVAL;
-
-    new = xmalloc(struct hvm_mmcfg);
-    if ( !new )
-        return -ENOMEM;
-
-    new->addr = addr + (start_bus << 20);
-    new->start_bus = start_bus;
-    new->segment = seg;
-    new->size = (end_bus - start_bus + 1) << 20;
-
-    write_lock(&d->arch.hvm.mmcfg_lock);
-    list_for_each_entry ( mmcfg, &d->arch.hvm.mmcfg_regions, next )
-        if ( new->addr < mmcfg->addr + mmcfg->size &&
-             mmcfg->addr < new->addr + new->size )
-        {
-            int ret = -EEXIST;
-
-            if ( new->addr == mmcfg->addr &&
-                 new->start_bus == mmcfg->start_bus &&
-                 new->segment == mmcfg->segment &&
-                 new->size == mmcfg->size )
-                ret = 0;
-            write_unlock(&d->arch.hvm.mmcfg_lock);
-            xfree(new);
-            return ret;
-        }
-
-    if ( list_empty(&d->arch.hvm.mmcfg_regions) )
-        register_mmio_handler(d, &vpci_mmcfg_ops);
-
-    list_add(&new->next, &d->arch.hvm.mmcfg_regions);
-    write_unlock(&d->arch.hvm.mmcfg_lock);
-
-    return 0;
-}
-
 /*
  * Local variables:
  * mode: C
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index 10c0f7a574..b2582bd3a0 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -1707,6 +1707,11 @@ int hvm_ioreq_register_mmcfg(struct domain *d, paddr_t addr,
     return 0;
 }
 
+bool hvm_is_mmcfg_address(const struct domain *d, paddr_t addr)
+{
+    return mmcfg_find(d, addr);
+}
+
 /*
  * Local variables:
  * mode: C
diff --git a/xen/arch/x86/physdev.c b/xen/arch/x86/physdev.c
index 3a3c15890b..a48b220fc3 100644
--- a/xen/arch/x86/physdev.c
+++ b/xen/arch/x86/physdev.c
@@ -11,6 +11,7 @@
 #include <asm/current.h>
 #include <asm/io_apic.h>
 #include <asm/msi.h>
+#include <asm/hvm/ioreq.h>
 #include <asm/hvm/irq.h>
 #include <asm/hypercall.h>
 #include <public/xen.h>
@@ -562,9 +563,9 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
              * For HVM (PVH) domains try to add the newly found MMCFG to the
              * domain.
              */
-            ret = register_vpci_mmcfg_handler(currd, info.address,
-                                              info.start_bus, info.end_bus,
-                                              info.segment);
+            ret = hvm_ioreq_register_mmcfg(currd, info.address,
+                                           info.start_bus, info.end_bus,
+                                           info.segment);
         }
 
         break;
diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index fd05075bb5..e0f3da91ce 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -244,7 +244,7 @@ static bool __hwdom_init hwdom_iommu_map(const struct domain *d,
      * TODO: runtime added MMCFG regions are not checked to make sure they
      * don't overlap with already mapped regions, thus preventing trapping.
      */
-    if ( has_vpci(d) && vpci_is_mmcfg_address(d, pfn_to_paddr(pfn)) )
+    if ( hvm_is_mmcfg_address(d, pfn_to_paddr(pfn)) )
         return false;
 
     return true;
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index 758d9420e7..510e3ee771 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -20,6 +20,8 @@
 #include <xen/sched.h>
 #include <xen/vpci.h>
 
+#include <asm/hvm/ioreq.h>
+
 /* Internal struct to store the emulated PCI registers. */
 struct vpci_register {
     vpci_read_t *read;
@@ -473,6 +475,58 @@ void vpci_write(pci_sbdf_t sbdf, unsigned int reg, unsigned int size,
     spin_unlock(&pdev->vpci->lock);
 }
 
+static int ioreq_handler(struct vcpu *v, ioreq_t *req)
+{
+    pci_sbdf_t sbdf;
+
+    if ( req->type != IOREQ_TYPE_PCI_CONFIG || req->data_is_ptr )
+    {
+        ASSERT_UNREACHABLE();
+        return X86EMUL_UNHANDLEABLE;
+    }
+
+    sbdf.sbdf = req->addr >> 32;
+
+    if ( req->dir )
+        req->data = vpci_read(sbdf, req->addr, req->size);
+    else
+        vpci_write(sbdf, req->addr, req->size, req->data);
+
+    return X86EMUL_OKAY;
+}
+
+int vpci_register_ioreq(struct domain *d)
+{
+    ioservid_t id;
+    int rc;
+
+    if ( !has_vpci(d) )
+        return 0;
+
+    rc = hvm_create_ioreq_server(d, HVM_IOREQSRV_BUFIOREQ_OFF, &id, true);
+    if ( rc )
+        return rc;
+
+    rc = hvm_add_ioreq_handler(d, id, ioreq_handler);
+    if ( rc )
+        return rc;
+
+    if ( is_hardware_domain(d) )
+    {
+        /* Handle all devices in vpci. */
+        rc = hvm_map_io_range_to_ioreq_server(d, id, XEN_DMOP_IO_RANGE_PCI,
+                                              0, ~(uint64_t)0, true);
+        if ( rc )
+            return rc;
+    }
+
+    rc = hvm_set_ioreq_server_state(d, id, true, true);
+    if ( rc )
+        return rc;
+
+    return rc;
+}
+
 /*
  * Local variables:
  * mode: C
diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
index 26f0489171..75a24f33bc 100644
--- a/xen/include/asm-x86/hvm/io.h
+++ b/xen/include/asm-x86/hvm/io.h
@@ -196,7 +196,7 @@ int register_vpci_mmcfg_handler(struct domain *d, paddr_t addr,
 void destroy_vpci_mmcfg(struct domain *d);
 
 /* Check if an address is between a MMCFG region for a domain. */
-bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr);
+bool hvm_is_mmcfg_address(const struct domain *d, paddr_t addr);
 
 #endif /* __ASM_X86_HVM_IO_H__ */
 
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 4cf233c779..666dd1ca68 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -23,6 +23,9 @@ typedef int vpci_register_init_t(struct pci_dev *dev);
   static vpci_register_init_t *const x##_entry  \
                __used_section(".data.vpci." p) = x
 
+/* Register vPCI handler wit ioreq. */
+int vpci_register_ioreq(struct domain *d);
+
 /* Add vPCI handlers to device. */
 int __must_check vpci_add_handlers(struct pci_dev *dev);
 
-- 
2.22.0


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

  parent reply index

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-21 14:58 [Xen-devel] [PATCH 0/7] ioreq: add support for internal servers Roger Pau Monne
2019-08-21 14:58 ` [Xen-devel] [PATCH 1/7] ioreq: add fields to allow internal ioreq servers Roger Pau Monne
2019-08-21 14:58 ` [Xen-devel] [PATCH 2/7] ioreq: add internal ioreq initialization support Roger Pau Monne
2019-08-21 16:24   ` Paul Durrant
2019-08-22  7:23     ` Roger Pau Monné
2019-08-22  8:30       ` Paul Durrant
2019-08-21 14:58 ` [Xen-devel] [PATCH 3/7] ioreq: allow dispatching ioreqs to internal servers Roger Pau Monne
2019-08-21 16:29   ` Paul Durrant
2019-08-22  7:40     ` Roger Pau Monné
2019-08-22  8:33       ` Paul Durrant
2019-08-21 14:59 ` [Xen-devel] [PATCH 4/7] ioreq: allow registering internal ioreq server handler Roger Pau Monne
2019-08-21 16:35   ` Paul Durrant
2019-08-22  7:43     ` Roger Pau Monné
2019-08-22  8:38       ` Paul Durrant
2019-08-21 14:59 ` [Xen-devel] [PATCH 5/7] ioreq: allow decoding accesses to MMCFG regions Roger Pau Monne
2019-08-21 14:59 ` Roger Pau Monne [this message]
2019-08-21 14:59 ` [Xen-devel] [PATCH 7/7] ioreq: provide support for long-running operations Roger Pau Monne
2019-08-22  9:15   ` Paul Durrant
2019-08-22 12:55     ` Roger Pau Monné
2019-08-22 13:07       ` Paul Durrant

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190821145903.45934-7-roger.pau@citrix.com \
    --to=roger.pau@citrix.com \
    --cc=George.Dunlap@eu.citrix.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=jbeulich@suse.com \
    --cc=julien.grall@arm.com \
    --cc=konrad.wilk@oracle.com \
    --cc=paul.durrant@citrix.com \
    --cc=sstabellini@kernel.org \
    --cc=tim@xen.org \
    --cc=wl@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Xen-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/xen-devel/0 xen-devel/git/0.git
	git clone --mirror https://lore.kernel.org/xen-devel/1 xen-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 xen-devel xen-devel/ https://lore.kernel.org/xen-devel \
		xen-devel@lists.xenproject.org xen-devel@lists.xen.org xen-devel@archiver.kernel.org
	public-inbox-index xen-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.xenproject.lists.xen-devel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox