* Re: [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table
2021-12-27 19:31 ` [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table Igor Mammedov
@ 2021-12-27 21:26 ` Philippe Mathieu-Daudé
2021-12-28 14:25 ` Denis Lisov
` (2 subsequent siblings)
3 siblings, 0 replies; 9+ messages in thread
From: Philippe Mathieu-Daudé @ 2021-12-27 21:26 UTC (permalink / raw)
To: Igor Mammedov, qemu-devel; +Cc: serat, dlenski, mst
On 12/27/21 20:31, Igor Mammedov wrote:
> if QEMU is started with used provided SLIC table blob,
>
> -acpitable sig=SLIC,oem_id='CRASH ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_rev=00000000,data=/dev/null
> it will assert with:
>
> hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed: (len <= maxlen)
>
> and following backtrace:
>
> ...
> build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e "CRASH ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61
> acpi_table_begin (desc=0x7fffffffd1b0, array=0x555556afe320) at hw/acpi/aml-build.c:1727
> build_fadt (tbl=0x555556afe320, linker=0x555557ca3830, f=0x7fffffffd318, oem_id=0x555556afdb2e "CRASH ME", oem_table_id=0x555556afdb34 "ME") at hw/acpi/aml-build.c:2064
> ...
>
> which happens due to acpi_table_begin() expecting NULL terminated
> oem_id and oem_table_id strings, which is normally the case, but
> in case of user provided SLIC table, oem_id points to table's blob
> directly and as result oem_id became longer than expected.
>
> Fix issue by handling oem_id consistently and make acpi_get_slic_oem()
> return NULL terminated strings.
>
> PS:
> After [1] refactoring, oem_id semantics became inconsistent, where
> NULL terminated string was coming from machine and old way pointer
> into byte array coming from -acpitable option. That used to work
> since build_header() wasn't expecting NULL terminated string and
> blindly copied the 1st 6 bytes only.
>
> However commit [2] broke that by replacing build_header() with
> acpi_table_begin(), which was expecting NULL terminated string
> and was checking oem_id size.
>
> 1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be changed")
> 2)
> Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use acpi_table_begin()/acpi_table_end() instead of build_header()")
> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/786
> Signed-off-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/core.c | 4 ++--
> hw/i386/acpi-build.c | 2 ++
> 2 files changed, 4 insertions(+), 2 deletions(-)
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table
2021-12-27 19:31 ` [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table Igor Mammedov
2021-12-27 21:26 ` Philippe Mathieu-Daudé
@ 2021-12-28 14:25 ` Denis Lisov
2021-12-30 22:30 ` Alexander Tsoy
2022-01-03 7:15 ` Igor Mammedov
3 siblings, 0 replies; 9+ messages in thread
From: Denis Lisov @ 2021-12-28 14:25 UTC (permalink / raw)
To: qemu-devel; +Cc: Igor Mammedov, dlenski, mst
On Monday, 27 December 2021 22:31:17 MSK Igor Mammedov wrote:
> if QEMU is started with used provided SLIC table blob,
>
> -acpitable sig=SLIC,oem_id='CRASH
> ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_rev=00
> 000000,data=/dev/null it will assert with:
>
> hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed: (len <=
> maxlen)
>
> and following backtrace:
>
> ...
> build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e "CRASH
> ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61 acpi_table_begin
> (desc=0x7fffffffd1b0, array=0x555556afe320) at hw/acpi/aml-build.c:1727
> build_fadt (tbl=0x555556afe320, linker=0x555557ca3830, f=0x7fffffffd318,
> oem_id=0x555556afdb2e "CRASH ME", oem_table_id=0x555556afdb34 "ME") at
> hw/acpi/aml-build.c:2064 ...
>
> which happens due to acpi_table_begin() expecting NULL terminated
> oem_id and oem_table_id strings, which is normally the case, but
> in case of user provided SLIC table, oem_id points to table's blob
> directly and as result oem_id became longer than expected.
>
> Fix issue by handling oem_id consistently and make acpi_get_slic_oem()
> return NULL terminated strings.
>
> PS:
> After [1] refactoring, oem_id semantics became inconsistent, where
> NULL terminated string was coming from machine and old way pointer
> into byte array coming from -acpitable option. That used to work
> since build_header() wasn't expecting NULL terminated string and
> blindly copied the 1st 6 bytes only.
>
> However commit [2] broke that by replacing build_header() with
> acpi_table_begin(), which was expecting NULL terminated string
> and was checking oem_id size.
>
> 1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be changed")
> 2)
> Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use
> acpi_table_begin()/acpi_table_end() instead of build_header()") Resolves:
> https://gitlab.com/qemu-project/qemu/-/issues/786
> Signed-off-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/core.c | 4 ++--
> hw/i386/acpi-build.c | 2 ++
> 2 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/hw/acpi/core.c b/hw/acpi/core.c
> index 1e004d0078..3e811bf03c 100644
> --- a/hw/acpi/core.c
> +++ b/hw/acpi/core.c
> @@ -345,8 +345,8 @@ int acpi_get_slic_oem(AcpiSlicOem *oem)
> struct acpi_table_header *hdr = (void *)(u - sizeof(hdr->_length));
>
> if (memcmp(hdr->sig, "SLIC", 4) == 0) {
> - oem->id = hdr->oem_id;
> - oem->table_id = hdr->oem_table_id;
> + oem->id = g_strndup(hdr->oem_id, 6);
> + oem->table_id = g_strndup(hdr->oem_table_id, 8);
> return 0;
> }
> }
> diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
> index 8383b83ee3..0234fe7588 100644
> --- a/hw/i386/acpi-build.c
> +++ b/hw/i386/acpi-build.c
> @@ -2723,6 +2723,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState
> *machine)
>
> /* Cleanup memory that's no longer used. */
> g_array_free(table_offsets, true);
> + g_free(slic_oem.id);
> + g_free(slic_oem.table_id);
> }
>
> static void acpi_ram_update(MemoryRegion *mr, GArray *data)
Tested-by: Denis Lisov <dennis.lissov@gmail.com>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table
2021-12-27 19:31 ` [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table Igor Mammedov
2021-12-27 21:26 ` Philippe Mathieu-Daudé
2021-12-28 14:25 ` Denis Lisov
@ 2021-12-30 22:30 ` Alexander Tsoy
2022-01-03 7:15 ` Igor Mammedov
3 siblings, 0 replies; 9+ messages in thread
From: Alexander Tsoy @ 2021-12-30 22:30 UTC (permalink / raw)
To: Igor Mammedov, qemu-devel; +Cc: dlenski, mst
В Пн, 27/12/2021 в 14:31 -0500, Igor Mammedov пишет:
> if QEMU is started with used provided SLIC table blob,
>
> -acpitable sig=SLIC,oem_id='CRASH
> ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_re
> v=00000000,data=/dev/null
> it will assert with:
>
> hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed:
> (len <= maxlen)
>
> and following backtrace:
>
> ...
> build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e
> "CRASH ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61
> acpi_table_begin (desc=0x7fffffffd1b0, array=0x555556afe320) at
> hw/acpi/aml-build.c:1727
> build_fadt (tbl=0x555556afe320, linker=0x555557ca3830,
> f=0x7fffffffd318, oem_id=0x555556afdb2e "CRASH ME",
> oem_table_id=0x555556afdb34 "ME") at hw/acpi/aml-build.c:2064
> ...
>
> which happens due to acpi_table_begin() expecting NULL terminated
> oem_id and oem_table_id strings, which is normally the case, but
> in case of user provided SLIC table, oem_id points to table's blob
> directly and as result oem_id became longer than expected.
>
> Fix issue by handling oem_id consistently and make acpi_get_slic_oem()
> return NULL terminated strings.
>
> PS:
> After [1] refactoring, oem_id semantics became inconsistent, where
> NULL terminated string was coming from machine and old way pointer
> into byte array coming from -acpitable option. That used to work
> since build_header() wasn't expecting NULL terminated string and
> blindly copied the 1st 6 bytes only.
>
> However commit [2] broke that by replacing build_header() with
> acpi_table_begin(), which was expecting NULL terminated string
> and was checking oem_id size.
>
> 1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be
> changed")
> 2)
> Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use
> acpi_table_begin()/acpi_table_end() instead of build_header()")
> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/786
> Signed-off-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/core.c | 4 ++--
> hw/i386/acpi-build.c | 2 ++
> 2 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/hw/acpi/core.c b/hw/acpi/core.c
> index 1e004d0078..3e811bf03c 100644
> --- a/hw/acpi/core.c
> +++ b/hw/acpi/core.c
> @@ -345,8 +345,8 @@ int acpi_get_slic_oem(AcpiSlicOem *oem)
> struct acpi_table_header *hdr = (void *)(u - sizeof(hdr-
> >_length));
>
> if (memcmp(hdr->sig, "SLIC", 4) == 0) {
> - oem->id = hdr->oem_id;
> - oem->table_id = hdr->oem_table_id;
> + oem->id = g_strndup(hdr->oem_id, 6);
> + oem->table_id = g_strndup(hdr->oem_table_id, 8);
> return 0;
> }
> }
> diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
> index 8383b83ee3..0234fe7588 100644
> --- a/hw/i386/acpi-build.c
> +++ b/hw/i386/acpi-build.c
> @@ -2723,6 +2723,8 @@ void acpi_build(AcpiBuildTables *tables,
> MachineState *machine)
>
> /* Cleanup memory that's no longer used. */
> g_array_free(table_offsets, true);
> + g_free(slic_oem.id);
> + g_free(slic_oem.table_id);
> }
>
> static void acpi_ram_update(MemoryRegion *mr, GArray *data)
Tested-by: Alexander Tsoy <alexander@tsoy.me>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table
2021-12-27 19:31 ` [PATCH 1/4] acpi: fix QEMU crash when started with SLIC table Igor Mammedov
` (2 preceding siblings ...)
2021-12-30 22:30 ` Alexander Tsoy
@ 2022-01-03 7:15 ` Igor Mammedov
3 siblings, 0 replies; 9+ messages in thread
From: Igor Mammedov @ 2022-01-03 7:15 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, mst
CCing, qemu-stable@
On Mon, 27 Dec 2021 14:31:17 -0500
Igor Mammedov <imammedo@redhat.com> wrote:
> if QEMU is started with used provided SLIC table blob,
>
> -acpitable sig=SLIC,oem_id='CRASH ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_rev=00000000,data=/dev/null
> it will assert with:
>
> hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed: (len <= maxlen)
>
> and following backtrace:
>
> ...
> build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e "CRASH ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61
> acpi_table_begin (desc=0x7fffffffd1b0, array=0x555556afe320) at hw/acpi/aml-build.c:1727
> build_fadt (tbl=0x555556afe320, linker=0x555557ca3830, f=0x7fffffffd318, oem_id=0x555556afdb2e "CRASH ME", oem_table_id=0x555556afdb34 "ME") at hw/acpi/aml-build.c:2064
> ...
>
> which happens due to acpi_table_begin() expecting NULL terminated
> oem_id and oem_table_id strings, which is normally the case, but
> in case of user provided SLIC table, oem_id points to table's blob
> directly and as result oem_id became longer than expected.
>
> Fix issue by handling oem_id consistently and make acpi_get_slic_oem()
> return NULL terminated strings.
>
> PS:
> After [1] refactoring, oem_id semantics became inconsistent, where
> NULL terminated string was coming from machine and old way pointer
> into byte array coming from -acpitable option. That used to work
> since build_header() wasn't expecting NULL terminated string and
> blindly copied the 1st 6 bytes only.
>
> However commit [2] broke that by replacing build_header() with
> acpi_table_begin(), which was expecting NULL terminated string
> and was checking oem_id size.
>
> 1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be changed")
> 2)
> Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use acpi_table_begin()/acpi_table_end() instead of build_header()")
> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/786
> Signed-off-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/core.c | 4 ++--
> hw/i386/acpi-build.c | 2 ++
> 2 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/hw/acpi/core.c b/hw/acpi/core.c
> index 1e004d0078..3e811bf03c 100644
> --- a/hw/acpi/core.c
> +++ b/hw/acpi/core.c
> @@ -345,8 +345,8 @@ int acpi_get_slic_oem(AcpiSlicOem *oem)
> struct acpi_table_header *hdr = (void *)(u - sizeof(hdr->_length));
>
> if (memcmp(hdr->sig, "SLIC", 4) == 0) {
> - oem->id = hdr->oem_id;
> - oem->table_id = hdr->oem_table_id;
> + oem->id = g_strndup(hdr->oem_id, 6);
> + oem->table_id = g_strndup(hdr->oem_table_id, 8);
> return 0;
> }
> }
> diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
> index 8383b83ee3..0234fe7588 100644
> --- a/hw/i386/acpi-build.c
> +++ b/hw/i386/acpi-build.c
> @@ -2723,6 +2723,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
>
> /* Cleanup memory that's no longer used. */
> g_array_free(table_offsets, true);
> + g_free(slic_oem.id);
> + g_free(slic_oem.table_id);
> }
>
> static void acpi_ram_update(MemoryRegion *mr, GArray *data)
^ permalink raw reply [flat|nested] 9+ messages in thread