| Message ID | 20240508005323.28811-1-yaoxt.fnst@fujitsu.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v3] mem/cxl_type3: support 3, 6, 12 and 16 interleave ways | expand |
ping. > -----Original Message----- > From: Yao Xingtao <yaoxt.fnst@fujitsu.com> > Sent: Wednesday, May 8, 2024 8:53 AM > To: jonathan.cameron@huawei.com; fan.ni@samsung.com > Cc: qemu-devel@nongnu.org; Yao, Xingtao/姚 幸涛 <yaoxt.fnst@fujitsu.com> > Subject: [PATCH v3] mem/cxl_type3: support 3, 6, 12 and 16 interleave ways > > Since the kernel does not check the interleave capability, a > 3-way, 6-way, 12-way or 16-way region can be create normally. > > Applications can access the memory of 16-way region normally because > qemu can convert hpa to dpa correctly for the power of 2 interleave > ways, after kernel implementing the check, this kind of region will > not be created any more. > > For non power of 2 interleave ways, applications could not access the > memory normally and may occur some unexpected behaviors, such as > segmentation fault. > > So implements this feature is needed. > > Link: > https://lore.kernel.org/linux-cxl/3e84b919-7631-d1db-3e1d-33000f3f3868@fujits > u.com/ > Signed-off-by: Yao Xingtao <yaoxt.fnst@fujitsu.com> > --- > hw/cxl/cxl-component-utils.c | 9 +++++++-- > hw/mem/cxl_type3.c | 15 +++++++++++---- > 2 files changed, 18 insertions(+), 6 deletions(-) > > diff --git a/hw/cxl/cxl-component-utils.c b/hw/cxl/cxl-component-utils.c > index cd116c0401..473895948b 100644 > --- a/hw/cxl/cxl-component-utils.c > +++ b/hw/cxl/cxl-component-utils.c > @@ -243,8 +243,13 @@ static void hdm_init_common(uint32_t *reg_state, > uint32_t *write_msk, > ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > INTERLEAVE_4K, 1); > ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > POISON_ON_ERR_CAP, 0); > - ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > 3_6_12_WAY, 0); > - ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 16_WAY, > 0); > + if (type == CXL2_TYPE3_DEVICE) { > + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > 3_6_12_WAY, 1); > + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > 16_WAY, 1); > + } else { > + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > 3_6_12_WAY, 0); > + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > 16_WAY, 0); > + } > ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, UIO, 0); > ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, > UIO_DECODER_COUNT, 0); > diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c > index 3e42490b6c..b755318838 100644 > --- a/hw/mem/cxl_type3.c > +++ b/hw/mem/cxl_type3.c > @@ -804,10 +804,17 @@ static bool cxl_type3_dpa(CXLType3Dev *ct3d, hwaddr > host_addr, uint64_t *dpa) > continue; > } > > - *dpa = dpa_base + > - ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | > - ((MAKE_64BIT_MASK(8 + ig + iw, 64 - 8 - ig - iw) & hpa_offset) > - >> iw)); > + if (iw < 8) { > + *dpa = dpa_base + > + ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | > + ((MAKE_64BIT_MASK(8 + ig + iw, 64 - 8 - ig - iw) & hpa_offset) > + >> iw)); > + } else { > + *dpa = dpa_base + > + ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | > + ((((MAKE_64BIT_MASK(ig + iw, 64 - ig - iw) & hpa_offset) > + >> (ig + iw)) / 3) << (ig + 8))); > + } > > return true; > } > -- > 2.37.3
diff --git a/hw/cxl/cxl-component-utils.c b/hw/cxl/cxl-component-utils.c index cd116c0401..473895948b 100644 --- a/hw/cxl/cxl-component-utils.c +++ b/hw/cxl/cxl-component-utils.c @@ -243,8 +243,13 @@ static void hdm_init_common(uint32_t *reg_state, uint32_t *write_msk, ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, INTERLEAVE_4K, 1); ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, POISON_ON_ERR_CAP, 0); - ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 3_6_12_WAY, 0); - ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 16_WAY, 0); + if (type == CXL2_TYPE3_DEVICE) { + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 3_6_12_WAY, 1); + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 16_WAY, 1); + } else { + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 3_6_12_WAY, 0); + ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, 16_WAY, 0); + } ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, UIO, 0); ARRAY_FIELD_DP32(reg_state, CXL_HDM_DECODER_CAPABILITY, UIO_DECODER_COUNT, 0); diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c index 3e42490b6c..b755318838 100644 --- a/hw/mem/cxl_type3.c +++ b/hw/mem/cxl_type3.c @@ -804,10 +804,17 @@ static bool cxl_type3_dpa(CXLType3Dev *ct3d, hwaddr host_addr, uint64_t *dpa) continue; } - *dpa = dpa_base + - ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | - ((MAKE_64BIT_MASK(8 + ig + iw, 64 - 8 - ig - iw) & hpa_offset) - >> iw)); + if (iw < 8) { + *dpa = dpa_base + + ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | + ((MAKE_64BIT_MASK(8 + ig + iw, 64 - 8 - ig - iw) & hpa_offset) + >> iw)); + } else { + *dpa = dpa_base + + ((MAKE_64BIT_MASK(0, 8 + ig) & hpa_offset) | + ((((MAKE_64BIT_MASK(ig + iw, 64 - ig - iw) & hpa_offset) + >> (ig + iw)) / 3) << (ig + 8))); + } return true; }
Since the kernel does not check the interleave capability, a 3-way, 6-way, 12-way or 16-way region can be create normally. Applications can access the memory of 16-way region normally because qemu can convert hpa to dpa correctly for the power of 2 interleave ways, after kernel implementing the check, this kind of region will not be created any more. For non power of 2 interleave ways, applications could not access the memory normally and may occur some unexpected behaviors, such as segmentation fault. So implements this feature is needed. Link: https://lore.kernel.org/linux-cxl/3e84b919-7631-d1db-3e1d-33000f3f3868@fujitsu.com/ Signed-off-by: Yao Xingtao <yaoxt.fnst@fujitsu.com> --- hw/cxl/cxl-component-utils.c | 9 +++++++-- hw/mem/cxl_type3.c | 15 +++++++++++---- 2 files changed, 18 insertions(+), 6 deletions(-)