From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Add relevant vpci register handlers when assigning PCI device to a domain
and remove those when de-assigning. This allows having different
handlers for different domains, e.g. hwdom and other guests.
Emulate guest BAR register values: this allows creating a guest view
of the registers and emulates size and properties probe as it is done
during PCI device enumeration by the guest.
All empty, IO and ROM BARs for guests are emulated by returning 0 on
reads and ignoring writes: this BARs are special with this respect as
their lower bits have special meaning, so returning default ~0 on read
may confuse guest OS.
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
---
Since v9:
- factored-out "fail" label introduction in init_bars()
- replaced #ifdef CONFIG_X86 with IS_ENABLED()
- do not pass bars[i] to empty_bar_read() handler
- store guest's BAR address instead of guests BAR register view
Since v6:
- unify the writing of the PCI_COMMAND register on the
error path into a label
- do not introduce bar_ignore_access helper and open code
- s/guest_bar_ignore_read/empty_bar_read
- update error message in guest_bar_write
- only setup empty_bar_read for IO if !x86
Since v5:
- make sure that the guest set address has the same page offset
as the physical address on the host
- remove guest_rom_{read|write} as those just implement the default
behaviour of the registers not being handled
- adjusted comment for struct vpci.addr field
- add guest handlers for BARs which are not handled and will otherwise
return ~0 on read and ignore writes. The BARs are special with this
respect as their lower bits have special meaning, so returning ~0
doesn't seem to be right
Since v4:
- updated commit message
- s/guest_addr/guest_reg
Since v3:
- squashed two patches: dynamic add/remove handlers and guest BAR
handler implementation
- fix guest BAR read of the high part of a 64bit BAR (Roger)
- add error handling to vpci_assign_device
- s/dom%pd/%pd
- blank line before return
Since v2:
- remove unneeded ifdefs for CONFIG_HAS_VPCI_GUEST_SUPPORT as more code
has been eliminated from being built on x86
Since v1:
- constify struct pci_dev where possible
- do not open code is_system_domain()
- simplify some code3. simplify
- use gdprintk + error code instead of gprintk
- gate vpci_bar_{add|remove}_handlers with CONFIG_HAS_VPCI_GUEST_SUPPORT,
so these do not get compiled for x86
- removed unneeded is_system_domain check
- re-work guest read/write to be much simpler and do more work on write
than read which is expected to be called more frequently
- removed one too obvious comment
---
xen/drivers/vpci/header.c | 131 +++++++++++++++++++++++++++++++++-----
xen/include/xen/vpci.h | 3 +
2 files changed, 118 insertions(+), 16 deletions(-)
diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
index e58bbdf68d..e96d7b2b37 100644
--- a/xen/drivers/vpci/header.c
+++ b/xen/drivers/vpci/header.c
@@ -477,6 +477,72 @@ static void cf_check bar_write(
pci_conf_write32(pdev->sbdf, reg, val);
}
+static void cf_check guest_bar_write(const struct pci_dev *pdev,
+ unsigned int reg, uint32_t val, void *data)
+{
+ struct vpci_bar *bar = data;
+ bool hi = false;
+ uint64_t guest_addr = bar->guest_addr;
+
+ if ( bar->type == VPCI_BAR_MEM64_HI )
+ {
+ ASSERT(reg > PCI_BASE_ADDRESS_0);
+ bar--;
+ hi = true;
+ }
+ else
+ {
+ val &= PCI_BASE_ADDRESS_MEM_MASK;
+ }
+
+ guest_addr &= ~(0xffffffffull << (hi ? 32 : 0));
+ guest_addr |= (uint64_t)val << (hi ? 32 : 0);
+
+ guest_addr &= ~(bar->size - 1) | ~PCI_BASE_ADDRESS_MEM_MASK;
+
+ /*
+ * Make sure that the guest set address has the same page offset
+ * as the physical address on the host or otherwise things won't work as
+ * expected.
+ */
+ if ( (guest_addr & (~PAGE_MASK)) != (bar->addr & ~PAGE_MASK) )
+ {
+ gprintk(XENLOG_WARNING,
+ "%pp: ignored BAR %zu write attempting to change page offset\n",
+ &pdev->sbdf, bar - pdev->vpci->header.bars + hi);
+ return;
+ }
+
+ bar->guest_addr = guest_addr;
+}
+
+static uint32_t cf_check guest_bar_read(const struct pci_dev *pdev,
+ unsigned int reg, void *data)
+{
+ const struct vpci_bar *bar = data;
+ uint32_t reg_val;
+
+ if ( bar->type == VPCI_BAR_MEM64_HI )
+ {
+ ASSERT(reg > PCI_BASE_ADDRESS_0);
+ bar--;
+ return bar->guest_addr >> 32;
+ }
+
+ reg_val = bar->guest_addr;
+ reg_val |= bar->type == VPCI_BAR_MEM32 ? PCI_BASE_ADDRESS_MEM_TYPE_32 :
+ PCI_BASE_ADDRESS_MEM_TYPE_64;
+ reg_val |= bar->prefetchable ? PCI_BASE_ADDRESS_MEM_PREFETCH : 0;
+
+ return reg_val;
+}
+
+static uint32_t cf_check empty_bar_read(const struct pci_dev *pdev,
+ unsigned int reg, void *data)
+{
+ return 0;
+}
+
static void cf_check rom_write(
const struct pci_dev *pdev, unsigned int reg, uint32_t val, void *data)
{
@@ -537,6 +603,7 @@ static int cf_check init_bars(struct pci_dev *pdev)
struct vpci_header *header = &pdev->vpci->header;
struct vpci_bar *bars = header->bars;
int rc;
+ bool is_hwdom = is_hardware_domain(pdev->domain);
ASSERT(rw_is_locked(&pdev->domain->pci_lock));
@@ -578,8 +645,10 @@ static int cf_check init_bars(struct pci_dev *pdev)
if ( i && bars[i - 1].type == VPCI_BAR_MEM64_LO )
{
bars[i].type = VPCI_BAR_MEM64_HI;
- rc = vpci_add_register(pdev->vpci, vpci_hw_read32, bar_write, reg,
- 4, &bars[i]);
+ rc = vpci_add_register(pdev->vpci,
+ is_hwdom ? vpci_hw_read32 : guest_bar_read,
+ is_hwdom ? bar_write : guest_bar_write,
+ reg, 4, &bars[i]);
if ( rc )
goto fail;
continue;
@@ -589,6 +658,15 @@ static int cf_check init_bars(struct pci_dev *pdev)
if ( (val & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO )
{
bars[i].type = VPCI_BAR_IO;
+
+ if ( !IS_ENABLED(CONFIG_X86) && !is_hwdom )
+ {
+ rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
+ reg, 4, NULL);
+ if ( rc )
+ goto fail;
+ }
+
continue;
}
if ( (val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) ==
@@ -605,6 +683,15 @@ static int cf_check init_bars(struct pci_dev *pdev)
if ( size == 0 )
{
bars[i].type = VPCI_BAR_EMPTY;
+
+ if ( !is_hwdom )
+ {
+ rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
+ reg, 4, NULL);
+ if ( rc )
+ goto fail;
+ }
+
continue;
}
@@ -612,28 +699,40 @@ static int cf_check init_bars(struct pci_dev *pdev)
bars[i].size = size;
bars[i].prefetchable = val & PCI_BASE_ADDRESS_MEM_PREFETCH;
- rc = vpci_add_register(pdev->vpci, vpci_hw_read32, bar_write, reg, 4,
- &bars[i]);
+ rc = vpci_add_register(pdev->vpci,
+ is_hwdom ? vpci_hw_read32 : guest_bar_read,
+ is_hwdom ? bar_write : guest_bar_write,
+ reg, 4, &bars[i]);
if ( rc )
goto fail;
}
- /* Check expansion ROM. */
- rc = pci_size_mem_bar(pdev->sbdf, rom_reg, &addr, &size, PCI_BAR_ROM);
- if ( rc > 0 && size )
+ /* TODO: Check expansion ROM, we do not handle ROM for guests for now. */
+ if ( is_hwdom )
{
- struct vpci_bar *rom = &header->bars[num_bars];
+ rc = pci_size_mem_bar(pdev->sbdf, rom_reg, &addr, &size, PCI_BAR_ROM);
+ if ( rc > 0 && size )
+ {
+ struct vpci_bar *rom = &header->bars[num_bars];
- rom->type = VPCI_BAR_ROM;
- rom->size = size;
- rom->addr = addr;
- header->rom_enabled = pci_conf_read32(pdev->sbdf, rom_reg) &
- PCI_ROM_ADDRESS_ENABLE;
+ rom->type = VPCI_BAR_ROM;
+ rom->size = size;
+ rom->addr = addr;
+ header->rom_enabled = pci_conf_read32(pdev->sbdf, rom_reg) &
+ PCI_ROM_ADDRESS_ENABLE;
- rc = vpci_add_register(pdev->vpci, vpci_hw_read32, rom_write, rom_reg,
- 4, rom);
+ rc = vpci_add_register(pdev->vpci, vpci_hw_read32, rom_write,
+ rom_reg, 4, rom);
+ if ( rc )
+ rom->type = VPCI_BAR_EMPTY;
+ }
+ }
+ else
+ {
+ rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
+ rom_reg, 4, NULL);
if ( rc )
- rom->type = VPCI_BAR_EMPTY;
+ goto fail;
}
return (cmd & PCI_COMMAND_MEMORY) ? modify_bars(pdev, cmd, false) : 0;
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 2a0ae34500..89f1e27f4f 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -67,7 +67,10 @@ struct vpci {
struct vpci_header {
/* Information about the PCI BARs of this device. */
struct vpci_bar {
+ /* Physical (host) address. */
uint64_t addr;
+ /* Guest address. */
+ uint64_t guest_addr;
uint64_t size;
enum {
VPCI_BAR_EMPTY,
--
2.41.0On Tue, Aug 29, 2023 at 11:19:43PM +0000, Volodymyr Babchuk wrote:
> From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
>
> Add relevant vpci register handlers when assigning PCI device to a domain
> and remove those when de-assigning. This allows having different
> handlers for different domains, e.g. hwdom and other guests.
>
> Emulate guest BAR register values: this allows creating a guest view
> of the registers and emulates size and properties probe as it is done
> during PCI device enumeration by the guest.
>
> All empty, IO and ROM BARs for guests are emulated by returning 0 on
> reads and ignoring writes: this BARs are special with this respect as
> their lower bits have special meaning, so returning default ~0 on read
> may confuse guest OS.
>
> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
> ---
> Since v9:
> - factored-out "fail" label introduction in init_bars()
> - replaced #ifdef CONFIG_X86 with IS_ENABLED()
> - do not pass bars[i] to empty_bar_read() handler
> - store guest's BAR address instead of guests BAR register view
> Since v6:
> - unify the writing of the PCI_COMMAND register on the
> error path into a label
> - do not introduce bar_ignore_access helper and open code
> - s/guest_bar_ignore_read/empty_bar_read
> - update error message in guest_bar_write
> - only setup empty_bar_read for IO if !x86
> Since v5:
> - make sure that the guest set address has the same page offset
> as the physical address on the host
> - remove guest_rom_{read|write} as those just implement the default
> behaviour of the registers not being handled
> - adjusted comment for struct vpci.addr field
> - add guest handlers for BARs which are not handled and will otherwise
> return ~0 on read and ignore writes. The BARs are special with this
> respect as their lower bits have special meaning, so returning ~0
> doesn't seem to be right
> Since v4:
> - updated commit message
> - s/guest_addr/guest_reg
> Since v3:
> - squashed two patches: dynamic add/remove handlers and guest BAR
> handler implementation
> - fix guest BAR read of the high part of a 64bit BAR (Roger)
> - add error handling to vpci_assign_device
> - s/dom%pd/%pd
> - blank line before return
> Since v2:
> - remove unneeded ifdefs for CONFIG_HAS_VPCI_GUEST_SUPPORT as more code
> has been eliminated from being built on x86
> Since v1:
> - constify struct pci_dev where possible
> - do not open code is_system_domain()
> - simplify some code3. simplify
> - use gdprintk + error code instead of gprintk
> - gate vpci_bar_{add|remove}_handlers with CONFIG_HAS_VPCI_GUEST_SUPPORT,
> so these do not get compiled for x86
> - removed unneeded is_system_domain check
> - re-work guest read/write to be much simpler and do more work on write
> than read which is expected to be called more frequently
> - removed one too obvious comment
> ---
> xen/drivers/vpci/header.c | 131 +++++++++++++++++++++++++++++++++-----
> xen/include/xen/vpci.h | 3 +
> 2 files changed, 118 insertions(+), 16 deletions(-)
>
> diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
> index e58bbdf68d..e96d7b2b37 100644
> --- a/xen/drivers/vpci/header.c
> +++ b/xen/drivers/vpci/header.c
> @@ -477,6 +477,72 @@ static void cf_check bar_write(
> pci_conf_write32(pdev->sbdf, reg, val);
> }
>
> +static void cf_check guest_bar_write(const struct pci_dev *pdev,
> + unsigned int reg, uint32_t val, void *data)
> +{
> + struct vpci_bar *bar = data;
> + bool hi = false;
> + uint64_t guest_addr = bar->guest_addr;
> +
> + if ( bar->type == VPCI_BAR_MEM64_HI )
> + {
> + ASSERT(reg > PCI_BASE_ADDRESS_0);
> + bar--;
> + hi = true;
> + }
> + else
> + {
> + val &= PCI_BASE_ADDRESS_MEM_MASK;
> + }
> +
> + guest_addr &= ~(0xffffffffull << (hi ? 32 : 0));
> + guest_addr |= (uint64_t)val << (hi ? 32 : 0);
> +
> + guest_addr &= ~(bar->size - 1) | ~PCI_BASE_ADDRESS_MEM_MASK;
I don't think you need to mask out PCI_BASE_ADDRESS_MEM_MASK here, as
you already do it if bar->type != VPCI_BAR_MEM64_HI for val.
> +
> + /*
> + * Make sure that the guest set address has the same page offset
> + * as the physical address on the host or otherwise things won't work as
> + * expected.
> + */
> + if ( (guest_addr & (~PAGE_MASK)) != (bar->addr & ~PAGE_MASK) )
PAGE_OFFSET() would be easier to read.
> + {
> + gprintk(XENLOG_WARNING,
> + "%pp: ignored BAR %zu write attempting to change page offset\n",
> + &pdev->sbdf, bar - pdev->vpci->header.bars + hi);
> + return;
> + }
> +
> + bar->guest_addr = guest_addr;
> +}
> +
> +static uint32_t cf_check guest_bar_read(const struct pci_dev *pdev,
> + unsigned int reg, void *data)
> +{
> + const struct vpci_bar *bar = data;
> + uint32_t reg_val;
> +
> + if ( bar->type == VPCI_BAR_MEM64_HI )
> + {
> + ASSERT(reg > PCI_BASE_ADDRESS_0);
> + bar--;
> + return bar->guest_addr >> 32;
> + }
> +
> + reg_val = bar->guest_addr;
> + reg_val |= bar->type == VPCI_BAR_MEM32 ? PCI_BASE_ADDRESS_MEM_TYPE_32 :
> + PCI_BASE_ADDRESS_MEM_TYPE_64;
> + reg_val |= bar->prefetchable ? PCI_BASE_ADDRESS_MEM_PREFETCH : 0;
> +
> + return reg_val;
> +}
> +
> +static uint32_t cf_check empty_bar_read(const struct pci_dev *pdev,
> + unsigned int reg, void *data)
> +{
> + return 0;
> +}
If we are going to gain a lot of helpers that return a fixed value it
might be worthwhile to introduce a helper that returns what gets
passed as 'data'. Let's leave it as you propose for now.
> +
> static void cf_check rom_write(
> const struct pci_dev *pdev, unsigned int reg, uint32_t val, void *data)
> {
> @@ -537,6 +603,7 @@ static int cf_check init_bars(struct pci_dev *pdev)
> struct vpci_header *header = &pdev->vpci->header;
> struct vpci_bar *bars = header->bars;
> int rc;
> + bool is_hwdom = is_hardware_domain(pdev->domain);
>
> ASSERT(rw_is_locked(&pdev->domain->pci_lock));
>
> @@ -578,8 +645,10 @@ static int cf_check init_bars(struct pci_dev *pdev)
> if ( i && bars[i - 1].type == VPCI_BAR_MEM64_LO )
> {
> bars[i].type = VPCI_BAR_MEM64_HI;
> - rc = vpci_add_register(pdev->vpci, vpci_hw_read32, bar_write, reg,
> - 4, &bars[i]);
> + rc = vpci_add_register(pdev->vpci,
> + is_hwdom ? vpci_hw_read32 : guest_bar_read,
> + is_hwdom ? bar_write : guest_bar_write,
> + reg, 4, &bars[i]);
> if ( rc )
> goto fail;
> continue;
> @@ -589,6 +658,15 @@ static int cf_check init_bars(struct pci_dev *pdev)
> if ( (val & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO )
> {
> bars[i].type = VPCI_BAR_IO;
> +
> + if ( !IS_ENABLED(CONFIG_X86) && !is_hwdom )
> + {
> + rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
> + reg, 4, NULL);
> + if ( rc )
> + goto fail;
For consistency you should also set bars[i].type = VPCI_BAR_EMPTY
here.
> + }
> +
> continue;
> }
> if ( (val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) ==
> @@ -605,6 +683,15 @@ static int cf_check init_bars(struct pci_dev *pdev)
> if ( size == 0 )
> {
> bars[i].type = VPCI_BAR_EMPTY;
> +
> + if ( !is_hwdom )
> + {
> + rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
> + reg, 4, NULL);
> + if ( rc )
> + goto fail;
> + }
> +
> continue;
> }
>
> @@ -612,28 +699,40 @@ static int cf_check init_bars(struct pci_dev *pdev)
> bars[i].size = size;
> bars[i].prefetchable = val & PCI_BASE_ADDRESS_MEM_PREFETCH;
>
> - rc = vpci_add_register(pdev->vpci, vpci_hw_read32, bar_write, reg, 4,
> - &bars[i]);
> + rc = vpci_add_register(pdev->vpci,
> + is_hwdom ? vpci_hw_read32 : guest_bar_read,
> + is_hwdom ? bar_write : guest_bar_write,
> + reg, 4, &bars[i]);
> if ( rc )
> goto fail;
> }
>
> - /* Check expansion ROM. */
> - rc = pci_size_mem_bar(pdev->sbdf, rom_reg, &addr, &size, PCI_BAR_ROM);
> - if ( rc > 0 && size )
> + /* TODO: Check expansion ROM, we do not handle ROM for guests for now. */
> + if ( is_hwdom )
> {
> - struct vpci_bar *rom = &header->bars[num_bars];
> + rc = pci_size_mem_bar(pdev->sbdf, rom_reg, &addr, &size, PCI_BAR_ROM);
> + if ( rc > 0 && size )
> + {
> + struct vpci_bar *rom = &header->bars[num_bars];
>
> - rom->type = VPCI_BAR_ROM;
> - rom->size = size;
> - rom->addr = addr;
> - header->rom_enabled = pci_conf_read32(pdev->sbdf, rom_reg) &
> - PCI_ROM_ADDRESS_ENABLE;
> + rom->type = VPCI_BAR_ROM;
> + rom->size = size;
> + rom->addr = addr;
> + header->rom_enabled = pci_conf_read32(pdev->sbdf, rom_reg) &
> + PCI_ROM_ADDRESS_ENABLE;
>
> - rc = vpci_add_register(pdev->vpci, vpci_hw_read32, rom_write, rom_reg,
> - 4, rom);
> + rc = vpci_add_register(pdev->vpci, vpci_hw_read32, rom_write,
> + rom_reg, 4, rom);
> + if ( rc )
> + rom->type = VPCI_BAR_EMPTY;
> + }
> + }
> + else
> + {
> + rc = vpci_add_register(pdev->vpci, empty_bar_read, NULL,
> + rom_reg, 4, NULL);
You should set the BAR type to VPCI_BAR_EMPTY here.
Thanks, Roger.
On 9/20/23 05:49, Roger Pau Monné wrote:
> On Tue, Aug 29, 2023 at 11:19:43PM +0000, Volodymyr Babchuk wrote:
>> diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
>> index e58bbdf68d..e96d7b2b37 100644
>> --- a/xen/drivers/vpci/header.c
>> +++ b/xen/drivers/vpci/header.c
>> +static uint32_t cf_check empty_bar_read(const struct pci_dev *pdev,
>> + unsigned int reg, void *data)
>> +{
>> + return 0;
>> +}
>
> If we are going to gain a lot of helpers that return a fixed value it
> might be worthwhile to introduce a helper that returns what gets
> passed as 'data'. Let's leave it as you propose for now.
For future reference, I introduce such a helper in the vPCI capabilities filtering series [1]. If that series happens gets committed before this one, it could be worthwhile making the switch. But since the helper is not upstream yet, +1 for leaving as is for now.
[1] https://lists.xenproject.org/archives/html/xen-devel/2023-09/msg00796.html
On 8/29/23 19:19, Volodymyr Babchuk wrote:
> diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
> index e58bbdf68d..e96d7b2b37 100644
> --- a/xen/drivers/vpci/header.c
> +++ b/xen/drivers/vpci/header.c
> @@ -477,6 +477,72 @@ static void cf_check bar_write(
> pci_conf_write32(pdev->sbdf, reg, val);
> }
>
> +static void cf_check guest_bar_write(const struct pci_dev *pdev,
> + unsigned int reg, uint32_t val, void *data)
> +{
> + struct vpci_bar *bar = data;
> + bool hi = false;
> + uint64_t guest_addr = bar->guest_addr;
> +
> + if ( bar->type == VPCI_BAR_MEM64_HI )
> + {
> + ASSERT(reg > PCI_BASE_ADDRESS_0);
> + bar--;
> + hi = true;
> + }
> + else
> + {
> + val &= PCI_BASE_ADDRESS_MEM_MASK;
> + }
> +
> + guest_addr &= ~(0xffffffffull << (hi ? 32 : 0));
Uppercase ULL on the constant to avoid a MISRA violation
© 2016 - 2026 Red Hat, Inc.