[PATCH AUTOSEL 5.10 01/53] clk: rockchip: rk3036: fix up the sclk_sfc parent error

[PATCH AUTOSEL 5.10 01/53] clk: rockchip: rk3036: fix up the sclk_sfc parent error

[Sasha Levin]

From: Jon Lin <jon.lin@rock-chips.com>

[ Upstream commit 0be3df186f870cbde56b223c1ad7892109c9c440 ]

Choose the correct pll

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Jon Lin <jon.lin@rock-chips.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20210713094456.23288-5-jon.lin@rock-chips.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/rockchip/clk-rk3036.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index 6a46f85ad837..1814be5ef574 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -120,6 +120,7 @@ PNAME(mux_pll_src_3plls_p)	= { "apll", "dpll", "gpll" };
 PNAME(mux_timer_p)		= { "xin24m", "pclk_peri_src" };
 
 PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p)	= { "apll", "dpll", "gpll", "usb480m" };
+PNAME(mux_pll_src_dmyapll_dpll_gpll_xin24_p)   = { "dummy_apll", "dpll", "gpll", "xin24m" };
 
 PNAME(mux_mmc_src_p)	= { "apll", "dpll", "gpll", "xin24m" };
 PNAME(mux_i2s_pre_p)	= { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
@@ -339,7 +340,7 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS, 10, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 4, GFLAGS),
 
-	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_apll_dpll_gpll_usb480m_p, 0,
+	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_dmyapll_dpll_gpll_xin24_p, 0,
 			RK2928_CLKSEL_CON(16), 0, 2, MFLAGS, 2, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 5, GFLAGS),
 
-- 
2.30.2


_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip

[PATCH AUTOSEL 5.10 01/53] clk: rockchip: rk3036: fix up the sclk_sfc parent error

[Sasha Levin]

From: Jon Lin <jon.lin@rock-chips.com>

[ Upstream commit 0be3df186f870cbde56b223c1ad7892109c9c440 ]

Choose the correct pll

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Jon Lin <jon.lin@rock-chips.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20210713094456.23288-5-jon.lin@rock-chips.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/rockchip/clk-rk3036.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index 6a46f85ad837..1814be5ef574 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -120,6 +120,7 @@ PNAME(mux_pll_src_3plls_p)	= { "apll", "dpll", "gpll" };
 PNAME(mux_timer_p)		= { "xin24m", "pclk_peri_src" };
 
 PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p)	= { "apll", "dpll", "gpll", "usb480m" };
+PNAME(mux_pll_src_dmyapll_dpll_gpll_xin24_p)   = { "dummy_apll", "dpll", "gpll", "xin24m" };
 
 PNAME(mux_mmc_src_p)	= { "apll", "dpll", "gpll", "xin24m" };
 PNAME(mux_i2s_pre_p)	= { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
@@ -339,7 +340,7 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS, 10, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 4, GFLAGS),
 
-	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_apll_dpll_gpll_usb480m_p, 0,
+	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_dmyapll_dpll_gpll_xin24_p, 0,
 			RK2928_CLKSEL_CON(16), 0, 2, MFLAGS, 2, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 5, GFLAGS),
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 01/53] clk: rockchip: rk3036: fix up the sclk_sfc parent error

[Sasha Levin]

From: Jon Lin <jon.lin@rock-chips.com>

[ Upstream commit 0be3df186f870cbde56b223c1ad7892109c9c440 ]

Choose the correct pll

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Jon Lin <jon.lin@rock-chips.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20210713094456.23288-5-jon.lin@rock-chips.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/rockchip/clk-rk3036.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index 6a46f85ad837..1814be5ef574 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -120,6 +120,7 @@ PNAME(mux_pll_src_3plls_p)	= { "apll", "dpll", "gpll" };
 PNAME(mux_timer_p)		= { "xin24m", "pclk_peri_src" };
 
 PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p)	= { "apll", "dpll", "gpll", "usb480m" };
+PNAME(mux_pll_src_dmyapll_dpll_gpll_xin24_p)   = { "dummy_apll", "dpll", "gpll", "xin24m" };
 
 PNAME(mux_mmc_src_p)	= { "apll", "dpll", "gpll", "xin24m" };
 PNAME(mux_i2s_pre_p)	= { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
@@ -339,7 +340,7 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS, 10, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 4, GFLAGS),
 
-	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_apll_dpll_gpll_usb480m_p, 0,
+	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_dmyapll_dpll_gpll_xin24_p, 0,
 			RK2928_CLKSEL_CON(16), 0, 2, MFLAGS, 2, 5, DFLAGS,
 			RK2928_CLKGATE_CON(10), 5, GFLAGS),
 
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.10 02/53] scsi: be2iscsi: Fix use-after-free during IP updates

[Sasha Levin]

From: Mike Christie <michael.christie@oracle.com>

[ Upstream commit 7b0ddc1346089b62b45e688e350c9e1c3f7a3ab2 ]

This fixes a bug found by Lv Yunlong where, because beiscsi_exec_nemb_cmd()
frees memory for the be_dma_mem cmd(), we can access freed memory when
beiscsi_if_clr_ip()/beiscsi_if_set_ip()'s call to beiscsi_exec_nemb_cmd()
fails and we access the freed req. This fixes the issue by having the
caller free the cmd's memory.

Link: https://lore.kernel.org/r/20210701190840.175120-1-michael.christie@oracle.com
Reported-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/be2iscsi/be_mgmt.c | 84 ++++++++++++++++++---------------
 1 file changed, 45 insertions(+), 39 deletions(-)

diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 96d6e384b2b2..c1f79125cd0c 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -235,8 +235,7 @@ static int beiscsi_exec_nemb_cmd(struct beiscsi_hba *phba,
 	wrb = alloc_mcc_wrb(phba, &tag);
 	if (!wrb) {
 		mutex_unlock(&ctrl->mbox_lock);
-		rc = -ENOMEM;
-		goto free_cmd;
+		return -ENOMEM;
 	}
 
 	sge = nonembedded_sgl(wrb);
@@ -269,24 +268,6 @@ static int beiscsi_exec_nemb_cmd(struct beiscsi_hba *phba,
 	/* copy the response, if any */
 	if (resp_buf)
 		memcpy(resp_buf, nonemb_cmd->va, resp_buf_len);
-	/**
-	 * This is special case of NTWK_GET_IF_INFO where the size of
-	 * response is not known. beiscsi_if_get_info checks the return
-	 * value to free DMA buffer.
-	 */
-	if (rc == -EAGAIN)
-		return rc;
-
-	/**
-	 * If FW is busy that is driver timed out, DMA buffer is saved with
-	 * the tag, only when the cmd completes this buffer is freed.
-	 */
-	if (rc == -EBUSY)
-		return rc;
-
-free_cmd:
-	dma_free_coherent(&ctrl->pdev->dev, nonemb_cmd->size,
-			    nonemb_cmd->va, nonemb_cmd->dma);
 	return rc;
 }
 
@@ -309,6 +290,19 @@ static int beiscsi_prep_nemb_cmd(struct beiscsi_hba *phba,
 	return 0;
 }
 
+static void beiscsi_free_nemb_cmd(struct beiscsi_hba *phba,
+				  struct be_dma_mem *cmd, int rc)
+{
+	/*
+	 * If FW is busy the DMA buffer is saved with the tag. When the cmd
+	 * completes this buffer is freed.
+	 */
+	if (rc == -EBUSY)
+		return;
+
+	dma_free_coherent(&phba->ctrl.pdev->dev, cmd->size, cmd->va, cmd->dma);
+}
+
 static void __beiscsi_eq_delay_compl(struct beiscsi_hba *phba, unsigned int tag)
 {
 	struct be_dma_mem *tag_mem;
@@ -344,8 +338,16 @@ int beiscsi_modify_eq_delay(struct beiscsi_hba *phba,
 				cpu_to_le32(set_eqd[i].delay_multiplier);
 	}
 
-	return beiscsi_exec_nemb_cmd(phba, &nonemb_cmd,
-				     __beiscsi_eq_delay_compl, NULL, 0);
+	rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, __beiscsi_eq_delay_compl,
+				   NULL, 0);
+	if (rc) {
+		/*
+		 * Only free on failure. Async cmds are handled like -EBUSY
+		 * where it's handled for us.
+		 */
+		beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
+	}
+	return rc;
 }
 
 /**
@@ -372,6 +374,7 @@ int beiscsi_get_initiator_name(struct beiscsi_hba *phba, char *name, bool cfg)
 		req->hdr.version = 1;
 	rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL,
 				   &resp, sizeof(resp));
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 	if (rc) {
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
@@ -449,7 +452,9 @@ static int beiscsi_if_mod_gw(struct beiscsi_hba *phba,
 	req->ip_addr.ip_type = ip_type;
 	memcpy(req->ip_addr.addr, gw,
 	       (ip_type < BEISCSI_IP_TYPE_V6) ? IP_V4_LEN : IP_V6_LEN);
-	return beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, NULL, 0);
+	rt_val = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, NULL, 0);
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rt_val);
+	return rt_val;
 }
 
 int beiscsi_if_set_gw(struct beiscsi_hba *phba, u32 ip_type, u8 *gw)
@@ -499,8 +504,10 @@ int beiscsi_if_get_gw(struct beiscsi_hba *phba, u32 ip_type,
 	req = nonemb_cmd.va;
 	req->ip_type = ip_type;
 
-	return beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL,
-				     resp, sizeof(*resp));
+	rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, resp,
+				   sizeof(*resp));
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
+	return rc;
 }
 
 static int
@@ -537,6 +544,7 @@ beiscsi_if_clr_ip(struct beiscsi_hba *phba,
 			    "BG_%d : failed to clear IP: rc %d status %d\n",
 			    rc, req->ip_params.ip_record.status);
 	}
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 	return rc;
 }
 
@@ -581,6 +589,7 @@ beiscsi_if_set_ip(struct beiscsi_hba *phba, u8 *ip,
 		if (req->ip_params.ip_record.status)
 			rc = -EINVAL;
 	}
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 	return rc;
 }
 
@@ -608,6 +617,7 @@ int beiscsi_if_en_static(struct beiscsi_hba *phba, u32 ip_type,
 		reldhcp->interface_hndl = phba->interface_handle;
 		reldhcp->ip_type = ip_type;
 		rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, NULL, 0);
+		beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 		if (rc < 0) {
 			beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_CONFIG,
 				    "BG_%d : failed to release existing DHCP: %d\n",
@@ -689,7 +699,7 @@ int beiscsi_if_en_dhcp(struct beiscsi_hba *phba, u32 ip_type)
 	dhcpreq->interface_hndl = phba->interface_handle;
 	dhcpreq->ip_type = ip_type;
 	rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, NULL, 0);
-
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 exit:
 	kfree(if_info);
 	return rc;
@@ -762,11 +772,8 @@ int beiscsi_if_get_info(struct beiscsi_hba *phba, int ip_type,
 				    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
 				    "BG_%d : Memory Allocation Failure\n");
 
-				/* Free the DMA memory for the IOCTL issuing */
-				dma_free_coherent(&phba->ctrl.pdev->dev,
-						    nonemb_cmd.size,
-						    nonemb_cmd.va,
-						    nonemb_cmd.dma);
+				beiscsi_free_nemb_cmd(phba, &nonemb_cmd,
+						      -ENOMEM);
 				return -ENOMEM;
 		}
 
@@ -781,15 +788,13 @@ int beiscsi_if_get_info(struct beiscsi_hba *phba, int ip_type,
 				      nonemb_cmd.va)->actual_resp_len;
 			ioctl_size += sizeof(struct be_cmd_req_hdr);
 
-			/* Free the previous allocated DMA memory */
-			dma_free_coherent(&phba->ctrl.pdev->dev, nonemb_cmd.size,
-					    nonemb_cmd.va,
-					    nonemb_cmd.dma);
-
+			beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 			/* Free the virtual memory */
 			kfree(*if_info);
-		} else
+		} else {
+			beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
 			break;
+		}
 	} while (true);
 	return rc;
 }
@@ -806,8 +811,9 @@ int mgmt_get_nic_conf(struct beiscsi_hba *phba,
 	if (rc)
 		return rc;
 
-	return beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL,
-				     nic, sizeof(*nic));
+	rc = beiscsi_exec_nemb_cmd(phba, &nonemb_cmd, NULL, nic, sizeof(*nic));
+	beiscsi_free_nemb_cmd(phba, &nonemb_cmd, rc);
+	return rc;
 }
 
 static void beiscsi_boot_process_compl(struct beiscsi_hba *phba,
-- 
2.30.2

[PATCH AUTOSEL 5.10 03/53] scsi: lpfc: Fix NVMe support reporting in log message

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit ae463b60235e7a5decffbb0bd7209952ccda78eb ]

The NVMe support indicator in log message 6422 is displaying a field that
was initialized but never set to indicate NVMe support.  Remove obsolete
nvme_support element from the lpfc_hba structure and change log message to
display NVMe support status as reported in SLI4 Config Parameters mailbox
command.

Link: https://lore.kernel.org/r/20210707184351.67872-2-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc.h      | 1 -
 drivers/scsi/lpfc/lpfc_init.c | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 93e507677bdc..86996c72f213 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -819,7 +819,6 @@ struct lpfc_hba {
 	uint8_t  wwpn[8];
 	uint32_t RandomData[7];
 	uint8_t  fcp_embed_io;
-	uint8_t  nvme_support;	/* Firmware supports NVME */
 	uint8_t  nvmet_support;	/* driver supports NVMET */
 #define LPFC_NVMET_MAX_PORTS	32
 	uint8_t  mds_diags_support;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 37612299a34a..003648661f3b 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -12126,7 +12126,6 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 					bf_get(cfg_xib, mbx_sli4_parameters),
 					phba->cfg_enable_fc4_type);
 fcponly:
-			phba->nvme_support = 0;
 			phba->nvmet_support = 0;
 			phba->cfg_nvmet_mrq = 0;
 			phba->cfg_nvme_seg_cnt = 0;
@@ -12184,7 +12183,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 			"6422 XIB %d PBDE %d: FCP %d NVME %d %d %d\n",
 			bf_get(cfg_xib, mbx_sli4_parameters),
 			phba->cfg_enable_pbde,
-			phba->fcp_embed_io, phba->nvme_support,
+			phba->fcp_embed_io, sli4_params->nvme,
 			phba->cfg_nvme_embed_cmd, phba->cfg_suppress_rsp);
 
 	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
-- 
2.30.2

[f2fs-dev] [PATCH AUTOSEL 5.10 04/53] f2fs: Revert "f2fs: Fix indefinite loop in f2fs_gc() v1"

[Sasha Levin]

From: Jia Yang <jiayang5@huawei.com>

[ Upstream commit 10d0786b39b3b91c4fbf8c2926e97ab456a4eea1 ]

This reverts commit 957fa47823dfe449c5a15a944e4e7a299a6601db.

The patch "f2fs: Fix indefinite loop in f2fs_gc()" v1 and v4 are all
merged. Patch v4 is test info for patch v1. Patch v1 doesn't work and
may cause that sbi->cur_victim_sec can't be resetted to NULL_SEGNO,
which makes SSR unable to get segment of sbi->cur_victim_sec.
So it should be reverted.

The mails record:
[1] https://lore.kernel.org/linux-f2fs-devel/7288dcd4-b168-7656-d1af-7e2cafa4f720@huawei.com/T/
[2] https://lore.kernel.org/linux-f2fs-devel/20190809153653.GD93481@jaegeuk-macbookpro.roam.corp.google.com/T/

Signed-off-by: Jia Yang <jiayang5@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/gc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e02affb5c0e7..343b9baf0d08 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1727,7 +1727,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 		round++;
 	}
 
-	if (gc_type == FG_GC && seg_freed)
+	if (gc_type == FG_GC)
 		sbi->cur_victim_sec = NULL_SEGNO;
 
 	if (sync)
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[PATCH AUTOSEL 5.10 04/53] f2fs: Revert "f2fs: Fix indefinite loop in f2fs_gc() v1"

[Sasha Levin]

From: Jia Yang <jiayang5@huawei.com>

[ Upstream commit 10d0786b39b3b91c4fbf8c2926e97ab456a4eea1 ]

This reverts commit 957fa47823dfe449c5a15a944e4e7a299a6601db.

The patch "f2fs: Fix indefinite loop in f2fs_gc()" v1 and v4 are all
merged. Patch v4 is test info for patch v1. Patch v1 doesn't work and
may cause that sbi->cur_victim_sec can't be resetted to NULL_SEGNO,
which makes SSR unable to get segment of sbi->cur_victim_sec.
So it should be reverted.

The mails record:
[1] https://lore.kernel.org/linux-f2fs-devel/7288dcd4-b168-7656-d1af-7e2cafa4f720@huawei.com/T/
[2] https://lore.kernel.org/linux-f2fs-devel/20190809153653.GD93481@jaegeuk-macbookpro.roam.corp.google.com/T/

Signed-off-by: Jia Yang <jiayang5@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/gc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e02affb5c0e7..343b9baf0d08 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1727,7 +1727,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 		round++;
 	}
 
-	if (gc_type == FG_GC && seg_freed)
+	if (gc_type == FG_GC)
 		sbi->cur_victim_sec = NULL_SEGNO;
 
 	if (sync)
-- 
2.30.2

[PATCH AUTOSEL 5.10 05/53] scsi: smartpqi: Fix ISR accessing uninitialized data

[Sasha Levin]

From: Mike McGowen <mike.mcgowen@microchip.com>

[ Upstream commit 0777a3fb98f0ea546561d04db4fd325248c39961 ]

Correct driver's ISR accessing a data structure member that has not been
fully initialized during driver initialization.

The pqi queue groups can have uninitialized members when an interrupt
fires. This has not resulted in any driver crashes. This was found during
our own internal testing. No bugs were ever filed.

Link: https://lore.kernel.org/r/20210714182847.50360-9-don.brace@microchip.com
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Signed-off-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 5083e5d2b467..8d6c26e6251b 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -7284,11 +7284,11 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 
 	pqi_init_operational_queues(ctrl_info);
 
-	rc = pqi_request_irqs(ctrl_info);
+	rc = pqi_create_queues(ctrl_info);
 	if (rc)
 		return rc;
 
-	rc = pqi_create_queues(ctrl_info);
+	rc = pqi_request_irqs(ctrl_info);
 	if (rc)
 		return rc;
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 06/53] iommu/amd: Fix printing of IOMMU events when rate limiting kicks in

[Sasha Levin]

From: Lennert Buytenhek <buytenh@wantstofly.org>

[ Upstream commit ee974d9625c405977ef5d9aedc476be1d0362ebf ]

For the printing of RMP_HW_ERROR / RMP_PAGE_FAULT / IO_PAGE_FAULT
events, the AMD IOMMU code uses such logic:

	if (pdev)
		dev_data = dev_iommu_priv_get(&pdev->dev);

	if (dev_data && __ratelimit(&dev_data->rs)) {
		pci_err(pdev, ...
	} else {
		printk_ratelimit() / pr_err{,_ratelimited}(...
	}

This means that if we receive an event for a PCI devid which actually
does have a struct pci_dev and an attached struct iommu_dev_data, but
rate limiting kicks in, we'll fall back to the non-PCI branch of the
test, and print the event in a different format.

Fix this by changing the logic to:

	if (dev_data) {
		if (__ratelimit(&dev_data->rs)) {
			pci_err(pdev, ...
		}
	} else {
		pr_err_ratelimited(...
	}

Suggested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/YPgk1dD1gPMhJXgY@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd/iommu.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 5f1195791cb1..4c97aa81b836 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -502,9 +502,11 @@ static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
-			vmg_tag, spa, flags);
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+				vmg_tag, spa, flags);
+		}
 	} else {
 		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
@@ -533,9 +535,11 @@ static void amd_iommu_report_rmp_fault(volatile u32 *event)
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
-			vmg_tag, gpa, flags_rmp, flags);
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+				vmg_tag, gpa, flags_rmp, flags);
+		}
 	} else {
 		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
@@ -557,11 +561,13 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
-			domain_id, address, flags);
-	} else if (printk_ratelimit()) {
-		pr_err("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
+				domain_id, address, flags);
+		}
+	} else {
+		pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			domain_id, address, flags);
 	}
-- 
2.30.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.10 06/53] iommu/amd: Fix printing of IOMMU events when rate limiting kicks in

[Sasha Levin]

From: Lennert Buytenhek <buytenh@wantstofly.org>

[ Upstream commit ee974d9625c405977ef5d9aedc476be1d0362ebf ]

For the printing of RMP_HW_ERROR / RMP_PAGE_FAULT / IO_PAGE_FAULT
events, the AMD IOMMU code uses such logic:

	if (pdev)
		dev_data = dev_iommu_priv_get(&pdev->dev);

	if (dev_data && __ratelimit(&dev_data->rs)) {
		pci_err(pdev, ...
	} else {
		printk_ratelimit() / pr_err{,_ratelimited}(...
	}

This means that if we receive an event for a PCI devid which actually
does have a struct pci_dev and an attached struct iommu_dev_data, but
rate limiting kicks in, we'll fall back to the non-PCI branch of the
test, and print the event in a different format.

Fix this by changing the logic to:

	if (dev_data) {
		if (__ratelimit(&dev_data->rs)) {
			pci_err(pdev, ...
		}
	} else {
		pr_err_ratelimited(...
	}

Suggested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/YPgk1dD1gPMhJXgY@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd/iommu.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 5f1195791cb1..4c97aa81b836 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -502,9 +502,11 @@ static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
-			vmg_tag, spa, flags);
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+				vmg_tag, spa, flags);
+		}
 	} else {
 		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
@@ -533,9 +535,11 @@ static void amd_iommu_report_rmp_fault(volatile u32 *event)
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
-			vmg_tag, gpa, flags_rmp, flags);
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+				vmg_tag, gpa, flags_rmp, flags);
+		}
 	} else {
 		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
@@ -557,11 +561,13 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
-	if (dev_data && __ratelimit(&dev_data->rs)) {
-		pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
-			domain_id, address, flags);
-	} else if (printk_ratelimit()) {
-		pr_err("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
+				domain_id, address, flags);
+		}
+	} else {
+		pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			domain_id, address, flags);
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.10 07/53] scsi: lpfc: Fix cq_id truncation in rq create

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit df3d78c3eb4eba13b3ef9740a8c664508ee644ae ]

On the newer hardware, CQ_ID values can be larger than seen on previous
generations. This exposed an issue in the driver where its definition of
cq_id in the RQ Create mailbox cmd was too small, thus the cq_id was
truncated, causing the command to fail.

Revise the RQ_CREATE CQ_ID field to its proper size (16 bits).

Link: https://lore.kernel.org/r/20210722221721.74388-3-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_hw4.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 47e832b7f2c2..5197111c04b5 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1552,7 +1552,7 @@ struct rq_context {
 #define lpfc_rq_context_hdr_size_WORD	word1
 	uint32_t word2;
 #define lpfc_rq_context_cq_id_SHIFT	16
-#define lpfc_rq_context_cq_id_MASK	0x000003FF
+#define lpfc_rq_context_cq_id_MASK	0x0000FFFF
 #define lpfc_rq_context_cq_id_WORD	word2
 #define lpfc_rq_context_buf_size_SHIFT	0
 #define lpfc_rq_context_buf_size_MASK	0x0000FFFF
-- 
2.30.2

[PATCH AUTOSEL 5.10 08/53] pinctrl: renesas: Fix pin control matching on R-Car H3e-2G

[Sasha Levin]

From: Geert Uytterhoeven <geert+renesas@glider.be>

[ Upstream commit 91d1be9fb7d667ae136f05cc645276eb2c9fa40e ]

As R-Car H3 ES1.x (R8A77950) and R-Car ES2.0+ (R8A77951) use the same
compatible value, the pin control driver relies on soc_device_match()
with soc_id = "r8a7795" and the (non)matching of revision = "ES1.*" to
match with and distinguish between the two SoC variants.  The
corresponding entries in the normal of_match_table are present only to
make the optional sanity checks work.

The R-Car H3e-2G (R8A779M1) SoC is a different grading of the R-Car H3
ES3.0 (R8A77951) SoC.  It uses the same compatible values for individual
devices, but has an additional compatible value for the root node.
When running on an R-Car H3e-2G SoC, soc_device_match() with soc_id =
"r8a7795" does not return a match.  Hence the pin control driver falls
back to the normal of_match_table, and, as the R8A77950 entry is listed
first, incorrectly uses the sub-driver for R-Car H3 ES1.x.

Fix this by moving the entry for R8A77951 before the entry for R8A77950.
Simplify sh_pfc_quirk_match() to only handle R-Car H3 ES1,x, as R-Car H3
ES2.0+ can now be matched using the normal of_match_table as well.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/6cdc5bfa424461105779b56f455387e03560cf66.1626707688.git.geert+renesas@glider.be
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pinctrl/renesas/core.c   | 29 ++++++++++++-----------------
 drivers/pinctrl/renesas/sh_pfc.h |  4 ++--
 2 files changed, 14 insertions(+), 19 deletions(-)

diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c
index c528c124fb0e..c2a2f1b3de06 100644
--- a/drivers/pinctrl/renesas/core.c
+++ b/drivers/pinctrl/renesas/core.c
@@ -581,17 +581,21 @@ static const struct of_device_id sh_pfc_of_table[] = {
 		.data = &r8a7794_pinmux_info,
 	},
 #endif
-/* Both r8a7795 entries must be present to make sanity checks work */
-#ifdef CONFIG_PINCTRL_PFC_R8A77950
+/*
+ * Both r8a7795 entries must be present to make sanity checks work, but only
+ * the first entry is actually used.
+ * R-Car H3 ES1.x is matched using soc_device_match() instead.
+ */
+#ifdef CONFIG_PINCTRL_PFC_R8A77951
 	{
 		.compatible = "renesas,pfc-r8a7795",
-		.data = &r8a77950_pinmux_info,
+		.data = &r8a77951_pinmux_info,
 	},
 #endif
-#ifdef CONFIG_PINCTRL_PFC_R8A77951
+#ifdef CONFIG_PINCTRL_PFC_R8A77950
 	{
 		.compatible = "renesas,pfc-r8a7795",
-		.data = &r8a77951_pinmux_info,
+		.data = &r8a77950_pinmux_info,
 	},
 #endif
 #ifdef CONFIG_PINCTRL_PFC_R8A77960
@@ -1085,26 +1089,20 @@ static inline void sh_pfc_check_driver(struct platform_driver *pdrv) {}
 #ifdef CONFIG_OF
 static const void *sh_pfc_quirk_match(void)
 {
-#if defined(CONFIG_PINCTRL_PFC_R8A77950) || \
-    defined(CONFIG_PINCTRL_PFC_R8A77951)
+#ifdef CONFIG_PINCTRL_PFC_R8A77950
 	const struct soc_device_attribute *match;
 	static const struct soc_device_attribute quirks[] = {
 		{
 			.soc_id = "r8a7795", .revision = "ES1.*",
 			.data = &r8a77950_pinmux_info,
 		},
-		{
-			.soc_id = "r8a7795",
-			.data = &r8a77951_pinmux_info,
-		},
-
 		{ /* sentinel */ }
 	};
 
 	match = soc_device_match(quirks);
 	if (match)
-		return match->data ?: ERR_PTR(-ENODEV);
-#endif /* CONFIG_PINCTRL_PFC_R8A77950 || CONFIG_PINCTRL_PFC_R8A77951 */
+		return match->data;
+#endif /* CONFIG_PINCTRL_PFC_R8A77950 */
 
 	return NULL;
 }
@@ -1119,9 +1117,6 @@ static int sh_pfc_probe(struct platform_device *pdev)
 #ifdef CONFIG_OF
 	if (pdev->dev.of_node) {
 		info = sh_pfc_quirk_match();
-		if (IS_ERR(info))
-			return PTR_ERR(info);
-
 		if (!info)
 			info = of_device_get_match_data(&pdev->dev);
 	} else
diff --git a/drivers/pinctrl/renesas/sh_pfc.h b/drivers/pinctrl/renesas/sh_pfc.h
index eff1bb872325..0d3f13230fe9 100644
--- a/drivers/pinctrl/renesas/sh_pfc.h
+++ b/drivers/pinctrl/renesas/sh_pfc.h
@@ -320,8 +320,8 @@ extern const struct sh_pfc_soc_info r8a7791_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7792_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7793_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7794_pinmux_info;
-extern const struct sh_pfc_soc_info r8a77950_pinmux_info __weak;
-extern const struct sh_pfc_soc_info r8a77951_pinmux_info __weak;
+extern const struct sh_pfc_soc_info r8a77950_pinmux_info;
+extern const struct sh_pfc_soc_info r8a77951_pinmux_info;
 extern const struct sh_pfc_soc_info r8a77960_pinmux_info;
 extern const struct sh_pfc_soc_info r8a77961_pinmux_info;
 extern const struct sh_pfc_soc_info r8a77965_pinmux_info;
-- 
2.30.2

[PATCH AUTOSEL 5.10 09/53] clk: mediatek: Fix asymmetrical PLL enable and disable control

[Sasha Levin]

From: Chun-Jie Chen <chun-jie.chen@mediatek.com>

[ Upstream commit 7cc4e1bbe300c5cf610ece8eca6c6751b8bc74db ]

In fact, the en_mask is a combination of divider enable mask
and pll enable bit(bit0).
Before this patch, we enabled both divider mask and bit0 in prepare(),
but only cleared the bit0 in unprepare().
In the future, we hope en_mask will only be used as divider enable mask.
The enable register(CON0) will be set in 2 steps:
first is divider mask, and then bit0 during prepare(), and vice versa.
But considering backward compatibility, at this stage we allow en_mask
to be a combination or a pure divider enable mask.
And then we will make en_mask a pure divider enable mask in another
following patch series.

Reviewed-by: Ikjoon Jang <ikjn@chromium.org>
Signed-off-by: Weiyi Lu <weiyi.lu@mediatek.com>
Signed-off-by: Chun-Jie Chen <chun-jie.chen@mediatek.com>
Link: https://lore.kernel.org/r/20210726105719.15793-7-chun-jie.chen@mediatek.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/mediatek/clk-pll.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c
index f440f2cd0b69..11ed5d1d1c36 100644
--- a/drivers/clk/mediatek/clk-pll.c
+++ b/drivers/clk/mediatek/clk-pll.c
@@ -238,6 +238,7 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	r = readl(pll->pwr_addr) | CON0_PWR_ON;
 	writel(r, pll->pwr_addr);
@@ -247,10 +248,15 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 	writel(r, pll->pwr_addr);
 	udelay(1);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r |= pll->data->en_mask;
+	r = readl(pll->base_addr + REG_CON0) | CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) | div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
 	__mtk_pll_tuner_enable(pll);
 
 	udelay(20);
@@ -268,6 +274,7 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	if (pll->data->flags & HAVE_RST_BAR) {
 		r = readl(pll->base_addr + REG_CON0);
@@ -277,8 +284,13 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 
 	__mtk_pll_tuner_disable(pll);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r &= ~CON0_BASE_EN;
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) & ~div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
+	r = readl(pll->base_addr + REG_CON0) & ~CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
 	r = readl(pll->pwr_addr) | CON0_ISO_EN;
-- 
2.30.2


_______________________________________________
Linux-mediatek mailing list
Linux-mediatek@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-mediatek

[PATCH AUTOSEL 5.10 09/53] clk: mediatek: Fix asymmetrical PLL enable and disable control

[Sasha Levin]

From: Chun-Jie Chen <chun-jie.chen@mediatek.com>

[ Upstream commit 7cc4e1bbe300c5cf610ece8eca6c6751b8bc74db ]

In fact, the en_mask is a combination of divider enable mask
and pll enable bit(bit0).
Before this patch, we enabled both divider mask and bit0 in prepare(),
but only cleared the bit0 in unprepare().
In the future, we hope en_mask will only be used as divider enable mask.
The enable register(CON0) will be set in 2 steps:
first is divider mask, and then bit0 during prepare(), and vice versa.
But considering backward compatibility, at this stage we allow en_mask
to be a combination or a pure divider enable mask.
And then we will make en_mask a pure divider enable mask in another
following patch series.

Reviewed-by: Ikjoon Jang <ikjn@chromium.org>
Signed-off-by: Weiyi Lu <weiyi.lu@mediatek.com>
Signed-off-by: Chun-Jie Chen <chun-jie.chen@mediatek.com>
Link: https://lore.kernel.org/r/20210726105719.15793-7-chun-jie.chen@mediatek.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/mediatek/clk-pll.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c
index f440f2cd0b69..11ed5d1d1c36 100644
--- a/drivers/clk/mediatek/clk-pll.c
+++ b/drivers/clk/mediatek/clk-pll.c
@@ -238,6 +238,7 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	r = readl(pll->pwr_addr) | CON0_PWR_ON;
 	writel(r, pll->pwr_addr);
@@ -247,10 +248,15 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 	writel(r, pll->pwr_addr);
 	udelay(1);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r |= pll->data->en_mask;
+	r = readl(pll->base_addr + REG_CON0) | CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) | div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
 	__mtk_pll_tuner_enable(pll);
 
 	udelay(20);
@@ -268,6 +274,7 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	if (pll->data->flags & HAVE_RST_BAR) {
 		r = readl(pll->base_addr + REG_CON0);
@@ -277,8 +284,13 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 
 	__mtk_pll_tuner_disable(pll);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r &= ~CON0_BASE_EN;
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) & ~div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
+	r = readl(pll->base_addr + REG_CON0) & ~CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
 	r = readl(pll->pwr_addr) | CON0_ISO_EN;
-- 
2.30.2

[PATCH AUTOSEL 5.10 09/53] clk: mediatek: Fix asymmetrical PLL enable and disable control

[Sasha Levin]

From: Chun-Jie Chen <chun-jie.chen@mediatek.com>

[ Upstream commit 7cc4e1bbe300c5cf610ece8eca6c6751b8bc74db ]

In fact, the en_mask is a combination of divider enable mask
and pll enable bit(bit0).
Before this patch, we enabled both divider mask and bit0 in prepare(),
but only cleared the bit0 in unprepare().
In the future, we hope en_mask will only be used as divider enable mask.
The enable register(CON0) will be set in 2 steps:
first is divider mask, and then bit0 during prepare(), and vice versa.
But considering backward compatibility, at this stage we allow en_mask
to be a combination or a pure divider enable mask.
And then we will make en_mask a pure divider enable mask in another
following patch series.

Reviewed-by: Ikjoon Jang <ikjn@chromium.org>
Signed-off-by: Weiyi Lu <weiyi.lu@mediatek.com>
Signed-off-by: Chun-Jie Chen <chun-jie.chen@mediatek.com>
Link: https://lore.kernel.org/r/20210726105719.15793-7-chun-jie.chen@mediatek.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/mediatek/clk-pll.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c
index f440f2cd0b69..11ed5d1d1c36 100644
--- a/drivers/clk/mediatek/clk-pll.c
+++ b/drivers/clk/mediatek/clk-pll.c
@@ -238,6 +238,7 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	r = readl(pll->pwr_addr) | CON0_PWR_ON;
 	writel(r, pll->pwr_addr);
@@ -247,10 +248,15 @@ static int mtk_pll_prepare(struct clk_hw *hw)
 	writel(r, pll->pwr_addr);
 	udelay(1);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r |= pll->data->en_mask;
+	r = readl(pll->base_addr + REG_CON0) | CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) | div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
 	__mtk_pll_tuner_enable(pll);
 
 	udelay(20);
@@ -268,6 +274,7 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 {
 	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
 	u32 r;
+	u32 div_en_mask;
 
 	if (pll->data->flags & HAVE_RST_BAR) {
 		r = readl(pll->base_addr + REG_CON0);
@@ -277,8 +284,13 @@ static void mtk_pll_unprepare(struct clk_hw *hw)
 
 	__mtk_pll_tuner_disable(pll);
 
-	r = readl(pll->base_addr + REG_CON0);
-	r &= ~CON0_BASE_EN;
+	div_en_mask = pll->data->en_mask & ~CON0_BASE_EN;
+	if (div_en_mask) {
+		r = readl(pll->base_addr + REG_CON0) & ~div_en_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
+	r = readl(pll->base_addr + REG_CON0) & ~CON0_BASE_EN;
 	writel(r, pll->base_addr + REG_CON0);
 
 	r = readl(pll->pwr_addr) | CON0_ISO_EN;
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.10 10/53] HID: usbhid: free raw_report buffers in usbhid_stop

[Sasha Levin]

From: Anirudh Rayabharam <mail@anirudhrb.com>

[ Upstream commit f7744fa16b96da57187dc8e5634152d3b63d72de ]

Free the unsent raw_report buffers when the device is removed.

Fixes a memory leak reported by syzbot at:
https://syzkaller.appspot.com/bug?id=7b4fa7cb1a7c2d3342a2a8a6c53371c8c418ab47

Reported-by: syzbot+47b26cd837ececfc666d@syzkaller.appspotmail.com
Tested-by: syzbot+47b26cd837ececfc666d@syzkaller.appspotmail.com
Signed-off-by: Anirudh Rayabharam <mail@anirudhrb.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/hid/usbhid/hid-core.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 8d4ac4b9fb9d..009a0469d54f 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -503,7 +503,7 @@ static void hid_ctrl(struct urb *urb)
 
 	if (unplug) {
 		usbhid->ctrltail = usbhid->ctrlhead;
-	} else {
+	} else if (usbhid->ctrlhead != usbhid->ctrltail) {
 		usbhid->ctrltail = (usbhid->ctrltail + 1) & (HID_CONTROL_FIFO_SIZE - 1);
 
 		if (usbhid->ctrlhead != usbhid->ctrltail &&
@@ -1221,9 +1221,20 @@ static void usbhid_stop(struct hid_device *hid)
 	mutex_lock(&usbhid->mutex);
 
 	clear_bit(HID_STARTED, &usbhid->iofl);
+
 	spin_lock_irq(&usbhid->lock);	/* Sync with error and led handlers */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
+	while (usbhid->ctrltail != usbhid->ctrlhead) {
+		if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_OUT) {
+			kfree(usbhid->ctrl[usbhid->ctrltail].raw_report);
+			usbhid->ctrl[usbhid->ctrltail].raw_report = NULL;
+		}
+
+		usbhid->ctrltail = (usbhid->ctrltail + 1) &
+			(HID_CONTROL_FIFO_SIZE - 1);
+	}
 	spin_unlock_irq(&usbhid->lock);
+
 	usb_kill_urb(usbhid->urbin);
 	usb_kill_urb(usbhid->urbout);
 	usb_kill_urb(usbhid->urbctrl);
-- 
2.30.2

[f2fs-dev] [PATCH AUTOSEL 5.10 11/53] f2fs: fix to force keeping write barrier for strict fsync mode

[Sasha Levin]

From: Chao Yu <chao@kernel.org>

[ Upstream commit 2787991516468bfafafb9bf2b45a848e6b202e7c ]

[1] https://www.mail-archive.com/linux-f2fs-devel@lists.sourceforge.net/msg15126.html

As [1] reported, if lower device doesn't support write barrier, in below
case:

- write page #0; persist
- overwrite page #0
- fsync
 - write data page #0 OPU into device's cache
 - write inode page into device's cache
 - issue flush

If SPO is triggered during flush command, inode page can be persisted
before data page #0, so that after recovery, inode page can be recovered
with new physical block address of data page #0, however there may
contains dummy data in new physical block address.

Then what user will see is: after overwrite & fsync + SPO, old data in
file was corrupted, if any user do care about such case, we can suggest
user to use STRICT fsync mode, in this mode, we will force to use atomic
write sematics to keep write order in between data/node and last node,
so that it avoids potential data corruption during fsync().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/file.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5c74b2997197..d712c9090808 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -299,6 +299,18 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 				f2fs_exist_written_data(sbi, ino, UPDATE_INO))
 			goto flush_out;
 		goto out;
+	} else {
+		/*
+		 * for OPU case, during fsync(), node can be persisted before
+		 * data when lower device doesn't support write barrier, result
+		 * in data corruption after SPO.
+		 * So for strict fsync mode, force to use atomic write sematics
+		 * to keep write order in between data/node and last node to
+		 * avoid potential data corruption.
+		 */
+		if (F2FS_OPTION(sbi).fsync_mode ==
+				FSYNC_MODE_STRICT && !atomic)
+			atomic = true;
 	}
 go_write:
 	/*
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[PATCH AUTOSEL 5.10 11/53] f2fs: fix to force keeping write barrier for strict fsync mode

[Sasha Levin]

From: Chao Yu <chao@kernel.org>

[ Upstream commit 2787991516468bfafafb9bf2b45a848e6b202e7c ]

[1] https://www.mail-archive.com/linux-f2fs-devel@lists.sourceforge.net/msg15126.html

As [1] reported, if lower device doesn't support write barrier, in below
case:

- write page #0; persist
- overwrite page #0
- fsync
 - write data page #0 OPU into device's cache
 - write inode page into device's cache
 - issue flush

If SPO is triggered during flush command, inode page can be persisted
before data page #0, so that after recovery, inode page can be recovered
with new physical block address of data page #0, however there may
contains dummy data in new physical block address.

Then what user will see is: after overwrite & fsync + SPO, old data in
file was corrupted, if any user do care about such case, we can suggest
user to use STRICT fsync mode, in this mode, we will force to use atomic
write sematics to keep write order in between data/node and last node,
so that it avoids potential data corruption during fsync().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/file.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5c74b2997197..d712c9090808 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -299,6 +299,18 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 				f2fs_exist_written_data(sbi, ino, UPDATE_INO))
 			goto flush_out;
 		goto out;
+	} else {
+		/*
+		 * for OPU case, during fsync(), node can be persisted before
+		 * data when lower device doesn't support write barrier, result
+		 * in data corruption after SPO.
+		 * So for strict fsync mode, force to use atomic write sematics
+		 * to keep write order in between data/node and last node to
+		 * avoid potential data corruption.
+		 */
+		if (F2FS_OPTION(sbi).fsync_mode ==
+				FSYNC_MODE_STRICT && !atomic)
+			atomic = true;
 	}
 go_write:
 	/*
-- 
2.30.2

[f2fs-dev] [PATCH AUTOSEL 5.10 12/53] f2fs: fix min_seq_blocks can not make sense in some scenes.

[Sasha Levin]

From: Laibin Qiu <qiulaibin@huawei.com>

[ Upstream commit dc675a97129c4d9d5af55a3d7f23d7e092b8e032 ]

F2FS have dirty page count control for batched sequential
write in writepages, and get the value of min_seq_blocks by
blocks_per_seg * segs_per_sec(segs_per_sec defaults to 1).
But in some scenes we set a lager section size, Min_seq_blocks
will become too large to achieve the expected effect(eg. 4thread
sequential write, the number of merge requests will be reduced).

Signed-off-by: Laibin Qiu <qiulaibin@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/segment.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d04b449978aa..730f028e8f49 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -5109,7 +5109,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
-	sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
+	sm_info->min_seq_blocks = sbi->blocks_per_seg;
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 	sm_info->min_ssr_sections = reserved_sections(sbi);
 
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[PATCH AUTOSEL 5.10 12/53] f2fs: fix min_seq_blocks can not make sense in some scenes.

[Sasha Levin]

From: Laibin Qiu <qiulaibin@huawei.com>

[ Upstream commit dc675a97129c4d9d5af55a3d7f23d7e092b8e032 ]

F2FS have dirty page count control for batched sequential
write in writepages, and get the value of min_seq_blocks by
blocks_per_seg * segs_per_sec(segs_per_sec defaults to 1).
But in some scenes we set a lager section size, Min_seq_blocks
will become too large to achieve the expected effect(eg. 4thread
sequential write, the number of merge requests will be reduced).

Signed-off-by: Laibin Qiu <qiulaibin@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/segment.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d04b449978aa..730f028e8f49 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -5109,7 +5109,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
-	sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
+	sm_info->min_seq_blocks = sbi->blocks_per_seg;
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 	sm_info->min_ssr_sections = reserved_sections(sbi);
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 13/53] scsi: ufs: Verify UIC locking requirements at runtime

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit 35c7d874f5993db04ce3aa310ae088f14b801eda ]

Instead of documenting the locking requirements of the UIC code as
comments, use lockdep_assert_held() such that lockdep verifies the lockdep
requirements at runtime if lockdep is enabled.

Link: https://lore.kernel.org/r/20210722033439.26550-8-bvanassche@acm.org
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/ufs/ufshcd.c | 16 +++++++++-------
 drivers/scsi/ufs/ufshcd.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 854c96e63007..b9ed7115a721 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2084,15 +2084,15 @@ static inline u8 ufshcd_get_upmcrs(struct ufs_hba *hba)
 }
 
 /**
- * ufshcd_dispatch_uic_cmd - Dispatch UIC commands to unipro layers
+ * ufshcd_dispatch_uic_cmd - Dispatch an UIC command to the Unipro layer
  * @hba: per adapter instance
  * @uic_cmd: UIC command
- *
- * Mutex must be held.
  */
 static inline void
 ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	WARN_ON(hba->active_uic_cmd);
 
 	hba->active_uic_cmd = uic_cmd;
@@ -2110,11 +2110,10 @@ ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 }
 
 /**
- * ufshcd_wait_for_uic_cmd - Wait complectioin of UIC command
+ * ufshcd_wait_for_uic_cmd - Wait for completion of an UIC command
  * @hba: per adapter instance
  * @uic_cmd: UIC command
  *
- * Must be called with mutex held.
  * Returns 0 only if success.
  */
 static int
@@ -2123,6 +2122,8 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	int ret;
 	unsigned long flags;
 
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	if (wait_for_completion_timeout(&uic_cmd->done,
 					msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
 		ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
@@ -2152,14 +2153,15 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  * @uic_cmd: UIC command
  * @completion: initialize the completion only if this is set to true
  *
- * Identical to ufshcd_send_uic_cmd() expect mutex. Must be called
- * with mutex held and host_lock locked.
  * Returns 0 only if success.
  */
 static int
 __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
 		      bool completion)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+	lockdep_assert_held(hba->host->host_lock);
+
 	if (!ufshcd_ready_for_uic_cmd(hba)) {
 		dev_err(hba->dev,
 			"Controller not ready to accept UIC commands\n");
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 812aa348751e..899a674b49fd 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -636,7 +636,7 @@ struct ufs_hba_variant_params {
  * @priv: pointer to variant specific private data
  * @irq: Irq number of the controller
  * @active_uic_cmd: handle of active UIC command
- * @uic_cmd_mutex: mutex for uic command
+ * @uic_cmd_mutex: mutex for UIC command
  * @tmf_tag_set: TMF tag set.
  * @tmf_queue: Used to allocate TMF tags.
  * @pwr_done: completion for power mode change
-- 
2.30.2


_______________________________________________
Linux-mediatek mailing list
Linux-mediatek@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-mediatek

[PATCH AUTOSEL 5.10 13/53] scsi: ufs: Verify UIC locking requirements at runtime

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit 35c7d874f5993db04ce3aa310ae088f14b801eda ]

Instead of documenting the locking requirements of the UIC code as
comments, use lockdep_assert_held() such that lockdep verifies the lockdep
requirements at runtime if lockdep is enabled.

Link: https://lore.kernel.org/r/20210722033439.26550-8-bvanassche@acm.org
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/ufs/ufshcd.c | 16 +++++++++-------
 drivers/scsi/ufs/ufshcd.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 854c96e63007..b9ed7115a721 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2084,15 +2084,15 @@ static inline u8 ufshcd_get_upmcrs(struct ufs_hba *hba)
 }
 
 /**
- * ufshcd_dispatch_uic_cmd - Dispatch UIC commands to unipro layers
+ * ufshcd_dispatch_uic_cmd - Dispatch an UIC command to the Unipro layer
  * @hba: per adapter instance
  * @uic_cmd: UIC command
- *
- * Mutex must be held.
  */
 static inline void
 ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	WARN_ON(hba->active_uic_cmd);
 
 	hba->active_uic_cmd = uic_cmd;
@@ -2110,11 +2110,10 @@ ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 }
 
 /**
- * ufshcd_wait_for_uic_cmd - Wait complectioin of UIC command
+ * ufshcd_wait_for_uic_cmd - Wait for completion of an UIC command
  * @hba: per adapter instance
  * @uic_cmd: UIC command
  *
- * Must be called with mutex held.
  * Returns 0 only if success.
  */
 static int
@@ -2123,6 +2122,8 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	int ret;
 	unsigned long flags;
 
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	if (wait_for_completion_timeout(&uic_cmd->done,
 					msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
 		ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
@@ -2152,14 +2153,15 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  * @uic_cmd: UIC command
  * @completion: initialize the completion only if this is set to true
  *
- * Identical to ufshcd_send_uic_cmd() expect mutex. Must be called
- * with mutex held and host_lock locked.
  * Returns 0 only if success.
  */
 static int
 __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
 		      bool completion)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+	lockdep_assert_held(hba->host->host_lock);
+
 	if (!ufshcd_ready_for_uic_cmd(hba)) {
 		dev_err(hba->dev,
 			"Controller not ready to accept UIC commands\n");
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 812aa348751e..899a674b49fd 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -636,7 +636,7 @@ struct ufs_hba_variant_params {
  * @priv: pointer to variant specific private data
  * @irq: Irq number of the controller
  * @active_uic_cmd: handle of active UIC command
- * @uic_cmd_mutex: mutex for uic command
+ * @uic_cmd_mutex: mutex for UIC command
  * @tmf_tag_set: TMF tag set.
  * @tmf_queue: Used to allocate TMF tags.
  * @pwr_done: completion for power mode change
-- 
2.30.2

[PATCH AUTOSEL 5.10 13/53] scsi: ufs: Verify UIC locking requirements at runtime

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit 35c7d874f5993db04ce3aa310ae088f14b801eda ]

Instead of documenting the locking requirements of the UIC code as
comments, use lockdep_assert_held() such that lockdep verifies the lockdep
requirements at runtime if lockdep is enabled.

Link: https://lore.kernel.org/r/20210722033439.26550-8-bvanassche@acm.org
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/ufs/ufshcd.c | 16 +++++++++-------
 drivers/scsi/ufs/ufshcd.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 854c96e63007..b9ed7115a721 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2084,15 +2084,15 @@ static inline u8 ufshcd_get_upmcrs(struct ufs_hba *hba)
 }
 
 /**
- * ufshcd_dispatch_uic_cmd - Dispatch UIC commands to unipro layers
+ * ufshcd_dispatch_uic_cmd - Dispatch an UIC command to the Unipro layer
  * @hba: per adapter instance
  * @uic_cmd: UIC command
- *
- * Mutex must be held.
  */
 static inline void
 ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	WARN_ON(hba->active_uic_cmd);
 
 	hba->active_uic_cmd = uic_cmd;
@@ -2110,11 +2110,10 @@ ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 }
 
 /**
- * ufshcd_wait_for_uic_cmd - Wait complectioin of UIC command
+ * ufshcd_wait_for_uic_cmd - Wait for completion of an UIC command
  * @hba: per adapter instance
  * @uic_cmd: UIC command
  *
- * Must be called with mutex held.
  * Returns 0 only if success.
  */
 static int
@@ -2123,6 +2122,8 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	int ret;
 	unsigned long flags;
 
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+
 	if (wait_for_completion_timeout(&uic_cmd->done,
 					msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
 		ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
@@ -2152,14 +2153,15 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  * @uic_cmd: UIC command
  * @completion: initialize the completion only if this is set to true
  *
- * Identical to ufshcd_send_uic_cmd() expect mutex. Must be called
- * with mutex held and host_lock locked.
  * Returns 0 only if success.
  */
 static int
 __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
 		      bool completion)
 {
+	lockdep_assert_held(&hba->uic_cmd_mutex);
+	lockdep_assert_held(hba->host->host_lock);
+
 	if (!ufshcd_ready_for_uic_cmd(hba)) {
 		dev_err(hba->dev,
 			"Controller not ready to accept UIC commands\n");
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 812aa348751e..899a674b49fd 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -636,7 +636,7 @@ struct ufs_hba_variant_params {
  * @priv: pointer to variant specific private data
  * @irq: Irq number of the controller
  * @active_uic_cmd: handle of active UIC command
- * @uic_cmd_mutex: mutex for uic command
+ * @uic_cmd_mutex: mutex for UIC command
  * @tmf_tag_set: TMF tag set.
  * @tmf_queue: Used to allocate TMF tags.
  * @pwr_done: completion for power mode change
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.10 14/53] cpuidle: pseries: Do not cap the CEDE0 latency in fixup_cede0_latency()

[Sasha Levin]

From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>

[ Upstream commit 71737a6c2a8f801622d2b71567d1ec1e4c5b40b8 ]

Currently in fixup_cede0_latency() code, we perform the fixup the
CEDE(0) exit latency value only if minimum advertized extended CEDE
latency values are less than 10us. This was done so as to not break
the expected behaviour on POWER8 platforms where the advertised
latency was higher than the default 10us, which would delay the SMT
folding on the core.

However, after the earlier patch "cpuidle/pseries: Fixup CEDE0 latency
only for POWER10 onwards", we can be sure that the fixup of CEDE0
latency is going to happen only from POWER10 onwards. Hence
unconditionally use the minimum exit latency provided by the platform.

Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1626676399-15975-3-git-send-email-ego@linux.vnet.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cpuidle/cpuidle-pseries.c | 59 ++++++++++++++++---------------
 1 file changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a2b5c6f60cf0..18747e5287c8 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -346,11 +346,9 @@ static int pseries_cpuidle_driver_init(void)
 static void __init fixup_cede0_latency(void)
 {
 	struct xcede_latency_payload *payload;
-	u64 min_latency_us;
+	u64 min_xcede_latency_us = UINT_MAX;
 	int i;
 
-	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
-
 	if (parse_cede_parameters())
 		return;
 
@@ -358,42 +356,45 @@ static void __init fixup_cede0_latency(void)
 		nr_xcede_records);
 
 	payload = &xcede_latency_parameter.payload;
+
+	/*
+	 * The CEDE idle state maps to CEDE(0). While the hypervisor
+	 * does not advertise CEDE(0) exit latency values, it does
+	 * advertise the latency values of the extended CEDE states.
+	 * We use the lowest advertised exit latency value as a proxy
+	 * for the exit latency of CEDE(0).
+	 */
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
+		u8 hint = record->hint;
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
 		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
 
-		if (latency_us == 0)
-			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
-
-		if (latency_us < min_latency_us)
-			min_latency_us = latency_us;
-	}
-
-	/*
-	 * By default, we assume that CEDE(0) has exit latency 10us,
-	 * since there is no way for us to query from the platform.
-	 *
-	 * However, if the wakeup latency of an Extended CEDE state is
-	 * smaller than 10us, then we can be sure that CEDE(0)
-	 * requires no more than that.
-	 *
-	 * Perform the fix-up.
-	 */
-	if (min_latency_us < dedicated_states[1].exit_latency) {
 		/*
-		 * We set a minimum of 1us wakeup latency for cede0 to
-		 * distinguish it from snooze
+		 * We expect the exit latency of an extended CEDE
+		 * state to be non-zero, it to since it takes at least
+		 * a few nanoseconds to wakeup the idle CPU and
+		 * dispatch the virtual processor into the Linux
+		 * Guest.
+		 *
+		 * So we consider only non-zero value for performing
+		 * the fixup of CEDE(0) latency.
 		 */
-		u64 cede0_latency = 1;
+		if (latency_us == 0) {
+			pr_warn("cpuidle: Skipping xcede record %d [hint=%d]. Exit latency = 0us\n",
+				i, hint);
+			continue;
+		}
 
-		if (min_latency_us > cede0_latency)
-			cede0_latency = min_latency_us - 1;
+		if (latency_us < min_xcede_latency_us)
+			min_xcede_latency_us = latency_us;
+	}
 
-		dedicated_states[1].exit_latency = cede0_latency;
-		dedicated_states[1].target_residency = 10 * (cede0_latency);
+	if (min_xcede_latency_us != UINT_MAX) {
+		dedicated_states[1].exit_latency = min_xcede_latency_us;
+		dedicated_states[1].target_residency = 10 * (min_xcede_latency_us);
 		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
-			cede0_latency);
+			min_xcede_latency_us);
 	}
 
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 14/53] cpuidle: pseries: Do not cap the CEDE0 latency in fixup_cede0_latency()

[Sasha Levin]

From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>

[ Upstream commit 71737a6c2a8f801622d2b71567d1ec1e4c5b40b8 ]

Currently in fixup_cede0_latency() code, we perform the fixup the
CEDE(0) exit latency value only if minimum advertized extended CEDE
latency values are less than 10us. This was done so as to not break
the expected behaviour on POWER8 platforms where the advertised
latency was higher than the default 10us, which would delay the SMT
folding on the core.

However, after the earlier patch "cpuidle/pseries: Fixup CEDE0 latency
only for POWER10 onwards", we can be sure that the fixup of CEDE0
latency is going to happen only from POWER10 onwards. Hence
unconditionally use the minimum exit latency provided by the platform.

Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1626676399-15975-3-git-send-email-ego@linux.vnet.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cpuidle/cpuidle-pseries.c | 59 ++++++++++++++++---------------
 1 file changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a2b5c6f60cf0..18747e5287c8 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -346,11 +346,9 @@ static int pseries_cpuidle_driver_init(void)
 static void __init fixup_cede0_latency(void)
 {
 	struct xcede_latency_payload *payload;
-	u64 min_latency_us;
+	u64 min_xcede_latency_us = UINT_MAX;
 	int i;
 
-	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
-
 	if (parse_cede_parameters())
 		return;
 
@@ -358,42 +356,45 @@ static void __init fixup_cede0_latency(void)
 		nr_xcede_records);
 
 	payload = &xcede_latency_parameter.payload;
+
+	/*
+	 * The CEDE idle state maps to CEDE(0). While the hypervisor
+	 * does not advertise CEDE(0) exit latency values, it does
+	 * advertise the latency values of the extended CEDE states.
+	 * We use the lowest advertised exit latency value as a proxy
+	 * for the exit latency of CEDE(0).
+	 */
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
+		u8 hint = record->hint;
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
 		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
 
-		if (latency_us == 0)
-			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
-
-		if (latency_us < min_latency_us)
-			min_latency_us = latency_us;
-	}
-
-	/*
-	 * By default, we assume that CEDE(0) has exit latency 10us,
-	 * since there is no way for us to query from the platform.
-	 *
-	 * However, if the wakeup latency of an Extended CEDE state is
-	 * smaller than 10us, then we can be sure that CEDE(0)
-	 * requires no more than that.
-	 *
-	 * Perform the fix-up.
-	 */
-	if (min_latency_us < dedicated_states[1].exit_latency) {
 		/*
-		 * We set a minimum of 1us wakeup latency for cede0 to
-		 * distinguish it from snooze
+		 * We expect the exit latency of an extended CEDE
+		 * state to be non-zero, it to since it takes at least
+		 * a few nanoseconds to wakeup the idle CPU and
+		 * dispatch the virtual processor into the Linux
+		 * Guest.
+		 *
+		 * So we consider only non-zero value for performing
+		 * the fixup of CEDE(0) latency.
 		 */
-		u64 cede0_latency = 1;
+		if (latency_us == 0) {
+			pr_warn("cpuidle: Skipping xcede record %d [hint=%d]. Exit latency = 0us\n",
+				i, hint);
+			continue;
+		}
 
-		if (min_latency_us > cede0_latency)
-			cede0_latency = min_latency_us - 1;
+		if (latency_us < min_xcede_latency_us)
+			min_xcede_latency_us = latency_us;
+	}
 
-		dedicated_states[1].exit_latency = cede0_latency;
-		dedicated_states[1].target_residency = 10 * (cede0_latency);
+	if (min_xcede_latency_us != UINT_MAX) {
+		dedicated_states[1].exit_latency = min_xcede_latency_us;
+		dedicated_states[1].target_residency = 10 * (min_xcede_latency_us);
 		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
-			cede0_latency);
+			min_xcede_latency_us);
 	}
 
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 15/53] powerpc: make the install target not depend on any build artifact

[Sasha Levin]

From: Masahiro Yamada <masahiroy@kernel.org>

[ Upstream commit 9bef456b20581e630ef9a13555ca04fed65a859d ]

The install target should not depend on any build artifact.

The reason is explained in commit 19514fc665ff ("arm, kbuild: make
"make install" not depend on vmlinux").

Change the PowerPC installation code in a similar way.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210729141937.445051-2-masahiroy@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/boot/Makefile   |  2 +-
 arch/powerpc/boot/install.sh | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index e4b364b5da9e..de18b4df3866 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -436,7 +436,7 @@ $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 	$(Q)rm -f $@; ln $< $@
 
 # Only install the vmlinux
-install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
+install:
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)"
 
 # Install the vmlinux and other built boot targets.
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index b6a256bc96ee..8d669cf1ccda 100644
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -21,6 +21,20 @@
 # Bail with error code if anything goes wrong
 set -e
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
-- 
2.30.2

[PATCH AUTOSEL 5.10 15/53] powerpc: make the install target not depend on any build artifact

[Sasha Levin]

From: Masahiro Yamada <masahiroy@kernel.org>

[ Upstream commit 9bef456b20581e630ef9a13555ca04fed65a859d ]

The install target should not depend on any build artifact.

The reason is explained in commit 19514fc665ff ("arm, kbuild: make
"make install" not depend on vmlinux").

Change the PowerPC installation code in a similar way.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210729141937.445051-2-masahiroy@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/boot/Makefile   |  2 +-
 arch/powerpc/boot/install.sh | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index e4b364b5da9e..de18b4df3866 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -436,7 +436,7 @@ $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 	$(Q)rm -f $@; ln $< $@
 
 # Only install the vmlinux
-install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
+install:
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)"
 
 # Install the vmlinux and other built boot targets.
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index b6a256bc96ee..8d669cf1ccda 100644
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -21,6 +21,20 @@
 # Bail with error code if anything goes wrong
 set -e
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
-- 
2.30.2

[f2fs-dev] [PATCH AUTOSEL 5.10 16/53] f2fs: fix to stop filesystem update once CP failed

[Sasha Levin]

From: Chao Yu <chao@kernel.org>

[ Upstream commit 91803392c732c43b5cf440e885ea89be7f5fecef ]

During f2fs_write_checkpoint(), once we failed in
f2fs_flush_nat_entries() or do_checkpoint(), metadata of filesystem
such as prefree bitmap, nat/sit version bitmap won't be recovered,
it may cause f2fs image to be inconsistent, let's just set CP error
flag to avoid further updates until we figure out a scheme to rollback
all metadatas in such condition.

Reported-by: Yangtao Li <frank.li@vivo.com>
Signed-off-by: Yangtao Li <frank.li@vivo.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/checkpoint.c | 12 +++++++++---
 fs/f2fs/f2fs.h       |  2 +-
 fs/f2fs/segment.c    | 15 +++++++++++++--
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b39bf416d511..4e1f6860ee95 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1620,8 +1620,11 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
 	err = f2fs_flush_nat_entries(sbi, cpc);
-	if (err)
+	if (err) {
+		f2fs_err(sbi, "f2fs_flush_nat_entries failed err:%d, stop checkpoint", err);
+		f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
 		goto stop;
+	}
 
 	f2fs_flush_sit_entries(sbi, cpc);
 
@@ -1629,10 +1632,13 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_save_inmem_curseg(sbi);
 
 	err = do_checkpoint(sbi, cpc);
-	if (err)
+	if (err) {
+		f2fs_err(sbi, "do_checkpoint failed err:%d, stop checkpoint", err);
+		f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
 		f2fs_release_discard_addrs(sbi);
-	else
+	} else {
 		f2fs_clear_prefree_segments(sbi, cpc);
+	}
 
 	f2fs_restore_inmem_curseg(sbi);
 stop:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2d7799bd30b1..95eef965bbce 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -514,7 +514,7 @@ enum {
 					 */
 };
 
-#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */
+#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush count */
 
 /* congestion wait timeout value, default: 20ms */
 #define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 730f028e8f49..0b2013709f8e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -767,11 +767,22 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
 		return 0;
 
 	for (i = 1; i < sbi->s_ndevs; i++) {
+		int count = DEFAULT_RETRY_IO_COUNT;
+
 		if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
 			continue;
-		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
-		if (ret)
+
+		do {
+			ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+			if (ret)
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
+		} while (ret && --count);
+
+		if (ret) {
+			f2fs_stop_checkpoint(sbi, false);
 			break;
+		}
 
 		spin_lock(&sbi->dev_lock);
 		f2fs_clear_bit(i, (char *)&sbi->dirty_device);
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[PATCH AUTOSEL 5.10 16/53] f2fs: fix to stop filesystem update once CP failed

[Sasha Levin]

From: Chao Yu <chao@kernel.org>

[ Upstream commit 91803392c732c43b5cf440e885ea89be7f5fecef ]

During f2fs_write_checkpoint(), once we failed in
f2fs_flush_nat_entries() or do_checkpoint(), metadata of filesystem
such as prefree bitmap, nat/sit version bitmap won't be recovered,
it may cause f2fs image to be inconsistent, let's just set CP error
flag to avoid further updates until we figure out a scheme to rollback
all metadatas in such condition.

Reported-by: Yangtao Li <frank.li@vivo.com>
Signed-off-by: Yangtao Li <frank.li@vivo.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/checkpoint.c | 12 +++++++++---
 fs/f2fs/f2fs.h       |  2 +-
 fs/f2fs/segment.c    | 15 +++++++++++++--
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b39bf416d511..4e1f6860ee95 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1620,8 +1620,11 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
 	err = f2fs_flush_nat_entries(sbi, cpc);
-	if (err)
+	if (err) {
+		f2fs_err(sbi, "f2fs_flush_nat_entries failed err:%d, stop checkpoint", err);
+		f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
 		goto stop;
+	}
 
 	f2fs_flush_sit_entries(sbi, cpc);
 
@@ -1629,10 +1632,13 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_save_inmem_curseg(sbi);
 
 	err = do_checkpoint(sbi, cpc);
-	if (err)
+	if (err) {
+		f2fs_err(sbi, "do_checkpoint failed err:%d, stop checkpoint", err);
+		f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
 		f2fs_release_discard_addrs(sbi);
-	else
+	} else {
 		f2fs_clear_prefree_segments(sbi, cpc);
+	}
 
 	f2fs_restore_inmem_curseg(sbi);
 stop:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2d7799bd30b1..95eef965bbce 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -514,7 +514,7 @@ enum {
 					 */
 };
 
-#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */
+#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush count */
 
 /* congestion wait timeout value, default: 20ms */
 #define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 730f028e8f49..0b2013709f8e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -767,11 +767,22 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
 		return 0;
 
 	for (i = 1; i < sbi->s_ndevs; i++) {
+		int count = DEFAULT_RETRY_IO_COUNT;
+
 		if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
 			continue;
-		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
-		if (ret)
+
+		do {
+			ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+			if (ret)
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
+		} while (ret && --count);
+
+		if (ret) {
+			f2fs_stop_checkpoint(sbi, false);
 			break;
+		}
 
 		spin_lock(&sbi->dev_lock);
 		f2fs_clear_bit(i, (char *)&sbi->dirty_device);
-- 
2.30.2

[PATCH AUTOSEL 5.10 17/53] MIPS: loongson2ef: don't build serial.o unconditionally

[Sasha Levin]

From: Randy Dunlap <rdunlap@infradead.org>

[ Upstream commit ad548993a66c498267695edd8b19a682be0e3a8b ]

LOONGSON_UART_BASE depends on EARLY_PRINTK || SERIAL_8250, but when
neither of these Kconfig symbols is set, the kernel build has errors:

../arch/mips/loongson2ef/common/serial.c: In function 'serial_init':
../arch/mips/loongson2ef/common/serial.c:66:25: error: 'loongson_uart_base' undeclared (first use in this function)
   66 |                         loongson_uart_base;
../arch/mips/loongson2ef/common/serial.c:66:25: note: each undeclared identifier is reported only once for each function it appears in
../arch/mips/loongson2ef/common/serial.c:68:41: error: '_loongson_uart_base' undeclared (first use in this function)
   68 |                         (void __iomem *)_loongson_uart_base;

Fix this by building serial.o only when one (or both) of these
Kconfig symbols is enabled.

Tested with:
	(a) EARLY_PRINTK=y, SERIAL_8250 not set;
	(b) EARLY_PRINTK=y, SERIAL_8250=y;
	(c) EARLY_PRINTK=y, SERIAL_8250=m.
	(d) EARLY_PRINTK not set, SERIAL_8250=y;
	(e) EARLY_PRINTK not set, SERIAL_8250=m;
	(f) EARLY_PRINTK not set, SERIAL_8250 not set.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: linux-mips@vger.kernel.org
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/mips/loongson2ef/common/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/mips/loongson2ef/common/Makefile b/arch/mips/loongson2ef/common/Makefile
index d5ab3e543ea3..30ea8b5ca685 100644
--- a/arch/mips/loongson2ef/common/Makefile
+++ b/arch/mips/loongson2ef/common/Makefile
@@ -4,12 +4,14 @@
 #
 
 obj-y += setup.o init.o env.o time.o reset.o irq.o \
-    bonito-irq.o mem.o machtype.o platform.o serial.o
+    bonito-irq.o mem.o machtype.o platform.o
 obj-$(CONFIG_PCI) += pci.o
 
 #
 # Serial port support
 #
+obj-$(CONFIG_LOONGSON_UART_BASE) += serial.o
+obj-$(CONFIG_EARLY_PRINTK) += serial.o
 obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
 obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 18/53] jbd2: fix portability problems caused by unaligned accesses

[Sasha Levin]

From: Theodore Ts'o <tytso@mit.edu>

[ Upstream commit a20d1cebb98bba75f2e34fddc768dd8712c1bded ]

This commit applies the e2fsck/recovery.c portions of commit
1e0c8ca7c08a ("e2fsck: fix portability problems caused by unaligned
accesses) from the e2fsprogs git tree.

The on-disk format for the ext4 journal can have unaigned 32-bit
integers.  This can happen when replaying a journal using a obsolete
checksum format (which was never popularly used, since the v3 format
replaced v2 while the metadata checksum feature was being stablized).

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/jbd2/recovery.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 1e07dfac4d81..25744f088a6c 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -196,7 +196,7 @@ static int jbd2_descriptor_block_csum_verify(journal_t *j, void *buf)
 static int count_tags(journal_t *journal, struct buffer_head *bh)
 {
 	char *			tagp;
-	journal_block_tag_t *	tag;
+	journal_block_tag_t	tag;
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
@@ -206,14 +206,14 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 	tagp = &bh->b_data[sizeof(journal_header_t)];
 
 	while ((tagp - bh->b_data + tag_bytes) <= size) {
-		tag = (journal_block_tag_t *) tagp;
+		memcpy(&tag, tagp, sizeof(tag));
 
 		nr++;
 		tagp += tag_bytes;
-		if (!(tag->t_flags & cpu_to_be16(JBD2_FLAG_SAME_UUID)))
+		if (!(tag.t_flags & cpu_to_be16(JBD2_FLAG_SAME_UUID)))
 			tagp += 16;
 
-		if (tag->t_flags & cpu_to_be16(JBD2_FLAG_LAST_TAG))
+		if (tag.t_flags & cpu_to_be16(JBD2_FLAG_LAST_TAG))
 			break;
 	}
 
@@ -433,9 +433,9 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 }
 
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
+				      journal_block_tag3_t *tag3,
 				      void *buf, __u32 sequence)
 {
-	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
@@ -496,7 +496,7 @@ static int do_one_pass(journal_t *journal,
 	while (1) {
 		int			flags;
 		char *			tagp;
-		journal_block_tag_t *	tag;
+		journal_block_tag_t	tag;
 		struct buffer_head *	obh;
 		struct buffer_head *	nbh;
 
@@ -613,8 +613,8 @@ static int do_one_pass(journal_t *journal,
 			       <= journal->j_blocksize - descr_csum_size) {
 				unsigned long io_block;
 
-				tag = (journal_block_tag_t *) tagp;
-				flags = be16_to_cpu(tag->t_flags);
+				memcpy(&tag, tagp, sizeof(tag));
+				flags = be16_to_cpu(tag.t_flags);
 
 				io_block = next_log_block++;
 				wrap(journal, next_log_block);
@@ -632,7 +632,7 @@ static int do_one_pass(journal_t *journal,
 
 					J_ASSERT(obh != NULL);
 					blocknr = read_tag_block(journal,
-								 tag);
+								 &tag);
 
 					/* If the block has been
 					 * revoked, then we're all done
@@ -647,8 +647,8 @@ static int do_one_pass(journal_t *journal,
 
 					/* Look for block corruption */
 					if (!jbd2_block_tag_csum_verify(
-						journal, tag, obh->b_data,
-						be32_to_cpu(tmp->h_sequence))) {
+			journal, &tag, (journal_block_tag3_t *)tagp,
+			obh->b_data, be32_to_cpu(tmp->h_sequence))) {
 						brelse(obh);
 						success = -EFSBADCRC;
 						printk(KERN_ERR "JBD2: Invalid "
-- 
2.30.2

[PATCH AUTOSEL 5.10 19/53] jbd2: fix clang warning in recovery.c

[Sasha Levin]

From: Theodore Ts'o <tytso@mit.edu>

[ Upstream commit 390add0cc9f4d7fda89cf3db7651717e82cf0afc ]

Remove unused variable store which was never used.

This fix is also in e2fsprogs commit 99a2294f85f0 ("e2fsck: value
stored to err is never read").

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/jbd2/recovery.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 25744f088a6c..48b5efd2ad45 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -760,7 +760,6 @@ static int do_one_pass(journal_t *journal,
 				 */
 				jbd_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n",
 					  next_commit_ID);
-				err = 0;
 				brelse(bh);
 				goto done;
 			}
-- 
2.30.2

[PATCH AUTOSEL 5.10 20/53] iommu: Fix race condition during default domain allocation

[Sasha Levin]

From: Ashish Mhetre <amhetre@nvidia.com>

[ Upstream commit 211ff31b3d33b56aa12937e898c9280d07daf0d9 ]

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_domain sometimes is getting allocated more
than once as call to iommu_alloc_default_domain() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_domain pointer, separate IOVA space and only one of the devices'
domain is used for translations from IOMMU. This causes accesses from other
device to fault or see incorrect translations.
Fix this by protecting iommu_alloc_default_domain() call with group->mutex
and let all devices with same SID share same iommu_domain.

Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-2-git-send-email-amhetre@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/iommu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index bcf060b5cf85..a103a503a4db 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -262,7 +262,9 @@ int iommu_probe_device(struct device *dev)
 	 * support default domains, so the return value is not yet
 	 * checked.
 	 */
+	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
+	mutex_unlock(&group->mutex);
 
 	if (group->default_domain) {
 		ret = __iommu_attach_device(group->default_domain, dev);
-- 
2.30.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.10 20/53] iommu: Fix race condition during default domain allocation

[Sasha Levin]

From: Ashish Mhetre <amhetre@nvidia.com>

[ Upstream commit 211ff31b3d33b56aa12937e898c9280d07daf0d9 ]

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_domain sometimes is getting allocated more
than once as call to iommu_alloc_default_domain() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_domain pointer, separate IOVA space and only one of the devices'
domain is used for translations from IOMMU. This causes accesses from other
device to fault or see incorrect translations.
Fix this by protecting iommu_alloc_default_domain() call with group->mutex
and let all devices with same SID share same iommu_domain.

Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-2-git-send-email-amhetre@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/iommu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index bcf060b5cf85..a103a503a4db 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -262,7 +262,9 @@ int iommu_probe_device(struct device *dev)
 	 * support default domains, so the return value is not yet
 	 * checked.
 	 */
+	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
+	mutex_unlock(&group->mutex);
 
 	if (group->default_domain) {
 		ret = __iommu_attach_device(group->default_domain, dev);
-- 
2.30.2

[PATCH AUTOSEL 5.10 21/53] iommu/arm-smmu: Fix race condition during iommu_group creation

[Sasha Levin]

From: Krishna Reddy <vdumpa@nvidia.com>

[ Upstream commit b1a1347912a742a4e1fcdc9df6302dd9dd2c3405 ]

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_group sometimes is getting allocated more
than once as call to arm_smmu_device_group() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_group and domain pointer, separate IOVA space and only one of the
devices' domain is used for translations from IOMMU. This causes accesses
from other device to fault or see incorrect translations.
Fix this by protecting iommu_group allocation from concurrency in
arm_smmu_device_group().

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-3-git-send-email-amhetre@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index df24bbe3ea4f..7a0fea12d0e5 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1475,6 +1475,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	struct iommu_group *group = NULL;
 	int i, idx;
 
+	mutex_lock(&smmu->stream_map_mutex);
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (group && smmu->s2crs[idx].group &&
 		    group != smmu->s2crs[idx].group)
@@ -1483,8 +1484,10 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		group = smmu->s2crs[idx].group;
 	}
 
-	if (group)
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
 		return iommu_group_ref_get(group);
+	}
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1498,6 +1501,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		for_each_cfg_sme(cfg, fwspec, i, idx)
 			smmu->s2crs[idx].group = group;
 
+	mutex_unlock(&smmu->stream_map_mutex);
 	return group;
 }
 
-- 
2.30.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.10 21/53] iommu/arm-smmu: Fix race condition during iommu_group creation

[Sasha Levin]

From: Krishna Reddy <vdumpa@nvidia.com>

[ Upstream commit b1a1347912a742a4e1fcdc9df6302dd9dd2c3405 ]

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_group sometimes is getting allocated more
than once as call to arm_smmu_device_group() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_group and domain pointer, separate IOVA space and only one of the
devices' domain is used for translations from IOMMU. This causes accesses
from other device to fault or see incorrect translations.
Fix this by protecting iommu_group allocation from concurrency in
arm_smmu_device_group().

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-3-git-send-email-amhetre@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index df24bbe3ea4f..7a0fea12d0e5 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1475,6 +1475,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	struct iommu_group *group = NULL;
 	int i, idx;
 
+	mutex_lock(&smmu->stream_map_mutex);
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (group && smmu->s2crs[idx].group &&
 		    group != smmu->s2crs[idx].group)
@@ -1483,8 +1484,10 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		group = smmu->s2crs[idx].group;
 	}
 
-	if (group)
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
 		return iommu_group_ref_get(group);
+	}
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1498,6 +1501,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		for_each_cfg_sme(cfg, fwspec, i, idx)
 			smmu->s2crs[idx].group = group;
 
+	mutex_unlock(&smmu->stream_map_mutex);
 	return group;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 21/53] iommu/arm-smmu: Fix race condition during iommu_group creation

[Sasha Levin]

From: Krishna Reddy <vdumpa@nvidia.com>

[ Upstream commit b1a1347912a742a4e1fcdc9df6302dd9dd2c3405 ]

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_group sometimes is getting allocated more
than once as call to arm_smmu_device_group() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_group and domain pointer, separate IOVA space and only one of the
devices' domain is used for translations from IOMMU. This causes accesses
from other device to fault or see incorrect translations.
Fix this by protecting iommu_group allocation from concurrency in
arm_smmu_device_group().

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-3-git-send-email-amhetre@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index df24bbe3ea4f..7a0fea12d0e5 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1475,6 +1475,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	struct iommu_group *group = NULL;
 	int i, idx;
 
+	mutex_lock(&smmu->stream_map_mutex);
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (group && smmu->s2crs[idx].group &&
 		    group != smmu->s2crs[idx].group)
@@ -1483,8 +1484,10 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		group = smmu->s2crs[idx].group;
 	}
 
-	if (group)
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
 		return iommu_group_ref_get(group);
+	}
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1498,6 +1501,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		for_each_cfg_sme(cfg, fwspec, i, idx)
 			smmu->s2crs[idx].group = group;
 
+	mutex_unlock(&smmu->stream_map_mutex);
 	return group;
 }
 
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.10 22/53] scsi: qla2xxx: Fix port type info

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit 01c97f2dd8fb4d2188c779a975031c0fe1ec061d ]

Over time, fcport->port_type became a flag field. The flags within this
field were not defined properly. This caused external tools to read wrong
info.

Link: https://lore.kernel.org/r/20210810043720.1137-8-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_def.h | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 4f0486fe30dd..119b5d76f97a 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2375,11 +2375,9 @@ struct mbx_24xx_entry {
  */
 typedef enum {
 	FCT_UNKNOWN,
-	FCT_RSCN,
-	FCT_SWITCH,
-	FCT_BROADCAST,
-	FCT_INITIATOR,
-	FCT_TARGET,
+	FCT_BROADCAST = 0x01,
+	FCT_INITIATOR = 0x02,
+	FCT_TARGET    = 0x04,
 	FCT_NVME_INITIATOR = 0x10,
 	FCT_NVME_TARGET = 0x20,
 	FCT_NVME_DISCOVERY = 0x40,
-- 
2.30.2

[PATCH AUTOSEL 5.10 23/53] scsi: qla2xxx: Fix unsafe removal from linked list

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit 0c9a5f3e42f75dbad5966aa59db935b694ab00d1 ]

On NPIV delete, the VPort is taken off a linked list in an unsafe manner.
The check for VPort refcount should be done behind lock before taking off
the element.

[ 2733.016907] general protection fault: 0000 [#1] SMP NOPTI
[ 2733.016908] qla2xxx [0000:22:00.1]-7088:27: VP[4] deleted.
[ 2733.016912] CPU: 22 PID: 23481 Comm: qla2xxx_15_dpc Kdump: loaded Tainted:
G           OE KX    5.3.18-47-default #1 SLE15-SP3
[ 2733.016914] Hardware name: Dell Inc. PowerEdge R7525/0PYVT1, BIOS 2.1.4 02/17/2021
[ 2733.016929] RIP: 0010:qla2x00_abort_isp+0x90/0x850 [qla2xxx]
[ 2733.016933] RSP: 0018:ffffb9cfc91efe98 EFLAGS: 00010087
[ 2733.016935] RAX: 0000000000000292 RBX: dead000000000100 RCX: 0000000000000000
[ 2733.016936] RDX: 0000000000000001 RSI: ffff944bfeb99558 RDI: ffff944bfc4b4488
[ 2733.016937] RBP: ffff944bfc4b2868 R08: 00000000000187a2 R09: 0000000000000001
[ 2733.016937] R10: ffffb9cfc91efcc8 R11: 0000000000000001 R12: ffff944bfc4b4000
[ 2733.016938] R13: ffff944bfc4b4870 R14: ffff944bfc4b4488 R15: ffff944bda895c80
[ 2733.016939] FS:  0000000000000000(0000) GS:ffff944bfeb80000(0000) knlGS:0000000000000000
[ 2733.016940] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2733.016940] CR2: 00007fc173e74458 CR3: 0000001ff57de000 CR4: 0000000000350ee0
[ 2733.016941] Call Trace:
[ 2733.016951]   qla2xxx_pci_error_detected+0x190/0x190 [qla2xxx]
[ 2733.016957]   qla2x00_do_dpc+0x560/0xa10 [qla2xxx]
[ 2733.016962]   kthread+0x10d/0x130
[ 2733.016963]   kthread_park+0xa0/0xa0
[ 2733.016966]   ret_from_fork+0x22/0x40

Link: https://lore.kernel.org/r/20210810043720.1137-9-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_init.c | 33 +++++++++++++++++---------
 drivers/scsi/qla2xxx/qla_mid.c  | 42 ++++++++++++++++++++-------------
 drivers/scsi/qla2xxx/qla_os.c   |  6 ++---
 3 files changed, 50 insertions(+), 31 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 6faf34fa6220..9d51ef4eae3f 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -6388,13 +6388,13 @@ void
 qla2x00_update_fcports(scsi_qla_host_t *base_vha)
 {
 	fc_port_t *fcport;
-	struct scsi_qla_host *vha;
+	struct scsi_qla_host *vha, *tvp;
 	struct qla_hw_data *ha = base_vha->hw;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
 	/* Go with deferred removal of rport references. */
-	list_for_each_entry(vha, &base_vha->hw->vp_list, list) {
+	list_for_each_entry_safe(vha, tvp, &base_vha->hw->vp_list, list) {
 		atomic_inc(&vha->vref_count);
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
 			if (fcport->drport &&
@@ -6739,7 +6739,8 @@ void
 qla2x00_quiesce_io(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct scsi_qla_host *vp;
+	struct scsi_qla_host *vp, *tvp;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_dpc, vha, 0x401d,
 	    "Quiescing I/O - ha=%p.\n", ha);
@@ -6748,8 +6749,18 @@ qla2x00_quiesce_io(scsi_qla_host_t *vha)
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
 		qla2x00_mark_all_devices_lost(vha);
-		list_for_each_entry(vp, &ha->vp_list, list)
+
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
+			atomic_inc(&vp->vref_count);
+			spin_unlock_irqrestore(&ha->vport_slock, flags);
+
 			qla2x00_mark_all_devices_lost(vp);
+
+			spin_lock_irqsave(&ha->vport_slock, flags);
+			atomic_dec(&vp->vref_count);
+		}
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
 	} else {
 		if (!atomic_read(&vha->loop_down_timer))
 			atomic_set(&vha->loop_down_timer,
@@ -6764,7 +6775,7 @@ void
 qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct scsi_qla_host *vp;
+	struct scsi_qla_host *vp, *tvp;
 	unsigned long flags;
 	fc_port_t *fcport;
 	u16 i;
@@ -6828,7 +6839,7 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 		qla2x00_mark_all_devices_lost(vha);
 
 		spin_lock_irqsave(&ha->vport_slock, flags);
-		list_for_each_entry(vp, &ha->vp_list, list) {
+		list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 			atomic_inc(&vp->vref_count);
 			spin_unlock_irqrestore(&ha->vport_slock, flags);
 
@@ -6850,7 +6861,7 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 		fcport->scan_state = 0;
 	}
 	spin_lock_irqsave(&ha->vport_slock, flags);
-	list_for_each_entry(vp, &ha->vp_list, list) {
+	list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 		atomic_inc(&vp->vref_count);
 		spin_unlock_irqrestore(&ha->vport_slock, flags);
 
@@ -6898,7 +6909,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 	int rval;
 	uint8_t        status = 0;
 	struct qla_hw_data *ha = vha->hw;
-	struct scsi_qla_host *vp;
+	struct scsi_qla_host *vp, *tvp;
 	struct req_que *req = ha->req_q_map[0];
 	unsigned long flags;
 
@@ -7030,7 +7041,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 		ql_dbg(ql_dbg_taskm, vha, 0x8022, "%s succeeded.\n", __func__);
 		qla2x00_configure_hba(vha);
 		spin_lock_irqsave(&ha->vport_slock, flags);
-		list_for_each_entry(vp, &ha->vp_list, list) {
+		list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 			if (vp->vp_idx) {
 				atomic_inc(&vp->vref_count);
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
@@ -8719,7 +8730,7 @@ qla82xx_restart_isp(scsi_qla_host_t *vha)
 {
 	int status, rval;
 	struct qla_hw_data *ha = vha->hw;
-	struct scsi_qla_host *vp;
+	struct scsi_qla_host *vp, *tvp;
 	unsigned long flags;
 
 	status = qla2x00_init_rings(vha);
@@ -8791,7 +8802,7 @@ qla82xx_restart_isp(scsi_qla_host_t *vha)
 		    "qla82xx_restart_isp succeeded.\n");
 
 		spin_lock_irqsave(&ha->vport_slock, flags);
-		list_for_each_entry(vp, &ha->vp_list, list) {
+		list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 			if (vp->vp_idx) {
 				atomic_inc(&vp->vref_count);
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c7caf322f445..787e0c0446a6 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -65,7 +65,7 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	uint16_t vp_id;
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags = 0;
-	u8 i;
+	u32 i, bailout;
 
 	mutex_lock(&ha->vport_lock);
 	/*
@@ -75,21 +75,29 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	 * ensures no active vp_list traversal while the vport is removed
 	 * from the queue)
 	 */
-	for (i = 0; i < 10; i++) {
-		if (wait_event_timeout(vha->vref_waitq,
-		    !atomic_read(&vha->vref_count), HZ) > 0)
+	bailout = 0;
+	for (i = 0; i < 500; i++) {
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		if (atomic_read(&vha->vref_count) == 0) {
+			list_del(&vha->list);
+			qlt_update_vp_map(vha, RESET_VP_IDX);
+			bailout = 1;
+		}
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
+
+		if (bailout)
 			break;
+		else
+			msleep(20);
 	}
-
-	spin_lock_irqsave(&ha->vport_slock, flags);
-	if (atomic_read(&vha->vref_count)) {
-		ql_dbg(ql_dbg_vport, vha, 0xfffa,
-		    "vha->vref_count=%u timeout\n", vha->vref_count.counter);
-		vha->vref_count = (atomic_t)ATOMIC_INIT(0);
+	if (!bailout) {
+		ql_log(ql_log_info, vha, 0xfffa,
+			"vha->vref_count=%u timeout\n", vha->vref_count.counter);
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		list_del(&vha->list);
+		qlt_update_vp_map(vha, RESET_VP_IDX);
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
 	}
-	list_del(&vha->list);
-	qlt_update_vp_map(vha, RESET_VP_IDX);
-	spin_unlock_irqrestore(&ha->vport_slock, flags);
 
 	vp_id = vha->vp_idx;
 	ha->num_vhosts--;
@@ -257,13 +265,13 @@ qla24xx_configure_vp(scsi_qla_host_t *vha)
 void
 qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb)
 {
-	scsi_qla_host_t *vha;
+	scsi_qla_host_t *vha, *tvp;
 	struct qla_hw_data *ha = rsp->hw;
 	int i = 0;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
-	list_for_each_entry(vha, &ha->vp_list, list) {
+	list_for_each_entry_safe(vha, tvp, &ha->vp_list, list) {
 		if (vha->vp_idx) {
 			if (test_bit(VPORT_DELETE, &vha->dpc_flags))
 				continue;
@@ -416,7 +424,7 @@ void
 qla2x00_do_dpc_all_vps(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	scsi_qla_host_t *vp;
+	scsi_qla_host_t *vp, *tvp;
 	unsigned long flags = 0;
 
 	if (vha->vp_idx)
@@ -430,7 +438,7 @@ qla2x00_do_dpc_all_vps(scsi_qla_host_t *vha)
 		return;
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
-	list_for_each_entry(vp, &ha->vp_list, list) {
+	list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 		if (vp->vp_idx) {
 			atomic_inc(&vp->vref_count);
 			spin_unlock_irqrestore(&ha->vport_slock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 21be50b35bc2..dd734992c726 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -7366,7 +7366,7 @@ static void qla_pci_error_cleanup(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 	struct qla_qpair *qpair = NULL;
-	struct scsi_qla_host *vp;
+	struct scsi_qla_host *vp, *tvp;
 	fc_port_t *fcport;
 	int i;
 	unsigned long flags;
@@ -7407,7 +7407,7 @@ static void qla_pci_error_cleanup(scsi_qla_host_t *vha)
 	qla2x00_mark_all_devices_lost(vha);
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
-	list_for_each_entry(vp, &ha->vp_list, list) {
+	list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 		atomic_inc(&vp->vref_count);
 		spin_unlock_irqrestore(&ha->vport_slock, flags);
 		qla2x00_mark_all_devices_lost(vp);
@@ -7421,7 +7421,7 @@ static void qla_pci_error_cleanup(scsi_qla_host_t *vha)
 		fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
-	list_for_each_entry(vp, &ha->vp_list, list) {
+	list_for_each_entry_safe(vp, tvp, &ha->vp_list, list) {
 		atomic_inc(&vp->vref_count);
 		spin_unlock_irqrestore(&ha->vport_slock, flags);
 		list_for_each_entry(fcport, &vp->vp_fcports, list)
-- 
2.30.2

[PATCH AUTOSEL 5.10 24/53] scsi: qla2xxx: Fix NPIV create erroneous error

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit a57214443f0f85639a0d9bbb8bd658d82dbf0927 ]

When user creates multiple NPIVs, the switch capabilities field is checked
before a vport is allowed to be created. This field is being toggled if a
switch scan is in progress. This creates erroneous reject of vport create.

Link: https://lore.kernel.org/r/20210810043720.1137-10-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_init.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 9d51ef4eae3f..d3526a247841 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4476,11 +4476,11 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 	/* initialize */
 	ha->min_external_loopid = SNS_FIRST_LOOP_ID;
 	ha->operating_mode = LOOP;
-	ha->switch_cap = 0;
 
 	switch (topo) {
 	case 0:
 		ql_dbg(ql_dbg_disc, vha, 0x200b, "HBA in NL topology.\n");
+		ha->switch_cap = 0;
 		ha->current_topology = ISP_CFG_NL;
 		strcpy(connect_type, "(Loop)");
 		break;
@@ -4494,6 +4494,7 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 
 	case 2:
 		ql_dbg(ql_dbg_disc, vha, 0x200d, "HBA in N P2P topology.\n");
+		ha->switch_cap = 0;
 		ha->operating_mode = P2P;
 		ha->current_topology = ISP_CFG_N;
 		strcpy(connect_type, "(N_Port-to-N_Port)");
@@ -4510,6 +4511,7 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 	default:
 		ql_dbg(ql_dbg_disc, vha, 0x200f,
 		    "HBA in unknown topology %x, using NL.\n", topo);
+		ha->switch_cap = 0;
 		ha->current_topology = ISP_CFG_NL;
 		strcpy(connect_type, "(Loop)");
 		break;
-- 
2.30.2

[PATCH AUTOSEL 5.10 25/53] ovl: skip checking lower file's i_writecount on truncate

[Sasha Levin]

From: Chengguang Xu <cgxu519@mykernel.net>

[ Upstream commit b71759ef1e1730db81dab98e9dab9455e8c7f5a2 ]

It is possible that a directory tree is shared between multiple overlay
instances as a lower layer.  In this case when one instance executes a file
residing on the lower layer, the other instance denies a truncate(2) call
on this file.

This only happens for truncate(2) and not for open(2) with the O_TRUNC
flag.

Fix this interference and inconsistency by removing the preliminary
i_writecount check before copy-up.

This means that unlike on normal filesystems truncate(argv[0]) will now
succeed.  If this ever causes a regression in a real world use case this
needs to be revisited.

One way to fix this properly would be to keep a correct i_writecount in the
overlay inode, but that is difficult due to memory mapping code only
dealing with the real file/inode.

Signed-off-by: Chengguang Xu <cgxu519@mykernel.net>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 Documentation/filesystems/overlayfs.rst | 3 +++
 fs/overlayfs/inode.c                    | 6 ------
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 137afeb3f581..7c40a135a919 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -427,6 +427,9 @@ b) If a file residing on a lower layer is opened for read-only and then
 memory mapped with MAP_SHARED, then subsequent changes to the file are not
 reflected in the memory mapping.
 
+c) If a file residing on a lower layer is being executed, then opening that
+file for write or truncating the file will not be denied with ETXTBSY.
+
 The following options allow overlayfs to act more like a standards
 compliant filesystem:
 
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 4fadafd8bdc1..6ee183e523c5 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -30,12 +30,6 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 		goto out;
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		struct inode *realinode = d_inode(ovl_dentry_real(dentry));
-
-		err = -ETXTBSY;
-		if (atomic_read(&realinode->i_writecount) < 0)
-			goto out_drop_write;
-
 		/* Truncate should trigger data copy up as well */
 		full_copy_up = true;
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.10 26/53] scsi: target: pscsi: Fix possible null-pointer dereference in pscsi_complete_cmd()

[Sasha Levin]

From: Tuo Li <islituo@gmail.com>

[ Upstream commit 0f99792c01d1d6d35b86e850e9ccadd98d6f3e0c ]

The return value of transport_kmap_data_sg() is assigned to the variable
buf:

  buf = transport_kmap_data_sg(cmd);

And then it is checked:

  if (!buf) {

This indicates that buf can be NULL. However, it is dereferenced in the
following statements:

  if (!(buf[3] & 0x80))
    buf[3] |= 0x80;
  if (!(buf[2] & 0x80))
    buf[2] |= 0x80;

To fix these possible null-pointer dereferences, dereference buf and call
transport_kunmap_data_sg() only when buf is not NULL.

Link: https://lore.kernel.org/r/20210810040414.248167-1-islituo@gmail.com
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Reviewed-by: Bodo Stroesser <bostroesser@gmail.com>
Signed-off-by: Tuo Li <islituo@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/target/target_core_pscsi.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index f10f0aa6cd37..19adf5812de5 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -622,17 +622,17 @@ static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status,
 			buf = transport_kmap_data_sg(cmd);
 			if (!buf) {
 				; /* XXX: TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE */
-			}
-
-			if (cdb[0] == MODE_SENSE_10) {
-				if (!(buf[3] & 0x80))
-					buf[3] |= 0x80;
 			} else {
-				if (!(buf[2] & 0x80))
-					buf[2] |= 0x80;
-			}
+				if (cdb[0] == MODE_SENSE_10) {
+					if (!(buf[3] & 0x80))
+						buf[3] |= 0x80;
+				} else {
+					if (!(buf[2] & 0x80))
+						buf[2] |= 0x80;
+				}
 
-			transport_kunmap_data_sg(cmd);
+				transport_kunmap_data_sg(cmd);
+			}
 		}
 	}
 after_mode_sense:
-- 
2.30.2

[PATCH AUTOSEL 5.10 27/53] iommu/vt-d: Add present bit check in pasid entry setup helpers

[Sasha Levin]

From: Liu Yi L <yi.l.liu@intel.com>

[ Upstream commit 423d39d8518c1bba12e0889a92beeddbb1502392 ]

The helper functions should not modify the pasid entries which are still
in use. Add a check against present bit.

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20210817042425.1784279-1-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210818134852.1847070-10-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel/pasid.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index fb911b6c418f..6db3400df484 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -523,6 +523,10 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 		devtlb_invalidation_with_pasid(iommu, dev, pasid);
 }
 
+/*
+ * This function flushes cache for a newly setup pasid table entry.
+ * Caller of it should not modify the in-use pasid table entries.
+ */
 static void pasid_flush_caches(struct intel_iommu *iommu,
 				struct pasid_entry *pte,
 			       u32 pasid, u16 did)
@@ -558,6 +562,10 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	if (WARN_ON(!pte))
 		return -EINVAL;
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 
 	/* Setup the first level page table pointer: */
@@ -654,6 +662,10 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_slptr(pte, pgd_val);
@@ -693,6 +705,10 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
-- 
2.30.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.10 27/53] iommu/vt-d: Add present bit check in pasid entry setup helpers

[Sasha Levin]

From: Liu Yi L <yi.l.liu@intel.com>

[ Upstream commit 423d39d8518c1bba12e0889a92beeddbb1502392 ]

The helper functions should not modify the pasid entries which are still
in use. Add a check against present bit.

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20210817042425.1784279-1-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210818134852.1847070-10-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel/pasid.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index fb911b6c418f..6db3400df484 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -523,6 +523,10 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 		devtlb_invalidation_with_pasid(iommu, dev, pasid);
 }
 
+/*
+ * This function flushes cache for a newly setup pasid table entry.
+ * Caller of it should not modify the in-use pasid table entries.
+ */
 static void pasid_flush_caches(struct intel_iommu *iommu,
 				struct pasid_entry *pte,
 			       u32 pasid, u16 did)
@@ -558,6 +562,10 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	if (WARN_ON(!pte))
 		return -EINVAL;
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 
 	/* Setup the first level page table pointer: */
@@ -654,6 +662,10 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_slptr(pte, pgd_val);
@@ -693,6 +705,10 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
+	/* Caller must ensure PASID entry is not in use. */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
-- 
2.30.2

[PATCH AUTOSEL 5.10 28/53] fs: dlm: fix return -EINTR on recovery stopped

[Sasha Levin]

From: Alexander Aring <aahringo@redhat.com>

[ Upstream commit aee742c9928ab4f5f4e0b00f41fb2d2cffae179e ]

This patch will return -EINTR instead of 1 if recovery is stopped. In
case of ping_members() the return value will be checked if the error is
-EINTR for signaling another recovery was triggered and the whole
recovery process will come to a clean end to process the next one.
Returning 1 will abort the recovery process and can leave the recovery
in a broken state.

It was reported with the following kernel log message attached and a gfs2
mount stopped working:

"dlm: bobvirt1: dlm_recover_members error 1"

whereas 1 was returned because of a conversion of "dlm_recovery_stopped()"
to an errno was missing which this patch will introduce. While on it all
other possible missing errno conversions at other places were added as
they are done as in other places.

It might be worth to check the error case at this recovery level,
because some of the functionality also returns -ENOBUFS and check why
recovery ends in a broken state. However this will fix the issue if
another recovery was triggered at some points of recovery handling.

Reported-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/dlm/dir.c      | 4 +++-
 fs/dlm/member.c   | 4 +++-
 fs/dlm/recoverd.c | 4 +++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 10c36ae1a8f9..45ebbe602bbf 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -85,8 +85,10 @@ int dlm_recover_directory(struct dlm_ls *ls)
 		for (;;) {
 			int left;
 			error = dlm_recovery_stopped(ls);
-			if (error)
+			if (error) {
+				error = -EINTR;
 				goto out_free;
+			}
 
 			error = dlm_rcom_names(ls, memb->nodeid,
 					       last_name, last_len);
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 7ad83deb4505..bbb048a03e3e 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -433,8 +433,10 @@ static int ping_members(struct dlm_ls *ls)
 
 	list_for_each_entry(memb, &ls->ls_nodes, list) {
 		error = dlm_recovery_stopped(ls);
-		if (error)
+		if (error) {
+			error = -EINTR;
 			break;
+		}
 		error = dlm_rcom_status(ls, memb->nodeid, 0);
 		if (error)
 			break;
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 85e245392715..97d052cea5a9 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -125,8 +125,10 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 	dlm_recover_waiters_pre(ls);
 
 	error = dlm_recovery_stopped(ls);
-	if (error)
+	if (error) {
+		error = -EINTR;
 		goto fail;
+	}
 
 	if (neg || dlm_no_directory(ls)) {
 		/*
-- 
2.30.2

[Cluster-devel] [PATCH AUTOSEL 5.10 28/53] fs: dlm: fix return -EINTR on recovery stopped

[Sasha Levin]

From: Alexander Aring <aahringo@redhat.com>

[ Upstream commit aee742c9928ab4f5f4e0b00f41fb2d2cffae179e ]

This patch will return -EINTR instead of 1 if recovery is stopped. In
case of ping_members() the return value will be checked if the error is
-EINTR for signaling another recovery was triggered and the whole
recovery process will come to a clean end to process the next one.
Returning 1 will abort the recovery process and can leave the recovery
in a broken state.

It was reported with the following kernel log message attached and a gfs2
mount stopped working:

"dlm: bobvirt1: dlm_recover_members error 1"

whereas 1 was returned because of a conversion of "dlm_recovery_stopped()"
to an errno was missing which this patch will introduce. While on it all
other possible missing errno conversions at other places were added as
they are done as in other places.

It might be worth to check the error case at this recovery level,
because some of the functionality also returns -ENOBUFS and check why
recovery ends in a broken state. However this will fix the issue if
another recovery was triggered at some points of recovery handling.

Reported-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/dlm/dir.c      | 4 +++-
 fs/dlm/member.c   | 4 +++-
 fs/dlm/recoverd.c | 4 +++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 10c36ae1a8f9..45ebbe602bbf 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -85,8 +85,10 @@ int dlm_recover_directory(struct dlm_ls *ls)
 		for (;;) {
 			int left;
 			error = dlm_recovery_stopped(ls);
-			if (error)
+			if (error) {
+				error = -EINTR;
 				goto out_free;
+			}
 
 			error = dlm_rcom_names(ls, memb->nodeid,
 					       last_name, last_len);
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 7ad83deb4505..bbb048a03e3e 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -433,8 +433,10 @@ static int ping_members(struct dlm_ls *ls)
 
 	list_for_each_entry(memb, &ls->ls_nodes, list) {
 		error = dlm_recovery_stopped(ls);
-		if (error)
+		if (error) {
+			error = -EINTR;
 			break;
+		}
 		error = dlm_rcom_status(ls, memb->nodeid, 0);
 		if (error)
 			break;
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 85e245392715..97d052cea5a9 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -125,8 +125,10 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 	dlm_recover_waiters_pre(ls);
 
 	error = dlm_recovery_stopped(ls);
-	if (error)
+	if (error) {
+		error = -EINTR;
 		goto fail;
+	}
 
 	if (neg || dlm_no_directory(ls)) {
 		/*
-- 
2.30.2

[PATCH AUTOSEL 5.10 29/53] HID: sony: Fix more ShanWan clone gamepads to not rumble when plugged in.

[Sasha Levin]

From: Ulrich Spörlein <uqs@FreeBSD.org>

[ Upstream commit bab94e97323baefe0afccad66e776f9c78b4f521 ]

The device string on these can differ, apparently, including typos. I've
bought 2 of these in 2012 and googling shows many folks out there with
that broken spelling in their dmesg.

Signed-off-by: Ulrich Spörlein <uqs@FreeBSD.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/hid/hid-sony.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 2f073f536070..cdff43defe88 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -2847,7 +2847,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (!strcmp(hdev->name, "FutureMax Dance Mat"))
 		quirks |= FUTUREMAX_DANCE_MAT;
 
-	if (!strcmp(hdev->name, "SHANWAN PS3 GamePad"))
+	if (!strcmp(hdev->name, "SHANWAN PS3 GamePad") ||
+	    !strcmp(hdev->name, "ShanWan PS(R) Ga`epad"))
 		quirks |= SHANWAN_GAMEPAD;
 
 	sc = devm_kzalloc(&hdev->dev, sizeof(*sc), GFP_KERNEL);
-- 
2.30.2

[PATCH AUTOSEL 5.10 30/53] MIPS: mscc: ocelot: disable all switch ports by default

[Sasha Levin]

From: Vladimir Oltean <vladimir.oltean@nxp.com>

[ Upstream commit 0181f6f19c6c35b24f1516d8db22f3bbce762633 ]

The ocelot switch driver used to ignore ports which do not have a
phy-handle property and not probe those, but this is not quite ok since
it is valid to not have a phy-handle property if there is a fixed-link.

It seems that checking for a phy-handle was a proxy for the proper check
which is for the status, but that doesn't make a lot of sense, since the
ocelot driver already iterates using for_each_available_child_of_node
which skips the disabled ports, so I have no idea.

Anyway, a widespread pattern in device trees is for a SoC dtsi to
disable by default all hardware, and let board dts files enable what is
used. So let's do that and enable only the ports with a phy-handle in
the pcb120 and pcb123 device tree files.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/mips/boot/dts/mscc/ocelot.dtsi       | 11 +++++++++++
 arch/mips/boot/dts/mscc/ocelot_pcb120.dts |  8 ++++++++
 arch/mips/boot/dts/mscc/ocelot_pcb123.dts |  4 ++++
 3 files changed, 23 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 535a98284dcb..e51db651af13 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -150,36 +150,47 @@ ethernet-ports {
 
 				port0: port@0 {
 					reg = <0>;
+					status = "disabled";
 				};
 				port1: port@1 {
 					reg = <1>;
+					status = "disabled";
 				};
 				port2: port@2 {
 					reg = <2>;
+					status = "disabled";
 				};
 				port3: port@3 {
 					reg = <3>;
+					status = "disabled";
 				};
 				port4: port@4 {
 					reg = <4>;
+					status = "disabled";
 				};
 				port5: port@5 {
 					reg = <5>;
+					status = "disabled";
 				};
 				port6: port@6 {
 					reg = <6>;
+					status = "disabled";
 				};
 				port7: port@7 {
 					reg = <7>;
+					status = "disabled";
 				};
 				port8: port@8 {
 					reg = <8>;
+					status = "disabled";
 				};
 				port9: port@9 {
 					reg = <9>;
+					status = "disabled";
 				};
 				port10: port@10 {
 					reg = <10>;
+					status = "disabled";
 				};
 			};
 		};
diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb120.dts b/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
index 897de5025d7f..d2dc6b3d923c 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
@@ -69,40 +69,48 @@ phy4: ethernet-phy@3 {
 };
 
 &port0 {
+	status = "okay";
 	phy-handle = <&phy0>;
 };
 
 &port1 {
+	status = "okay";
 	phy-handle = <&phy1>;
 };
 
 &port2 {
+	status = "okay";
 	phy-handle = <&phy2>;
 };
 
 &port3 {
+	status = "okay";
 	phy-handle = <&phy3>;
 };
 
 &port4 {
+	status = "okay";
 	phy-handle = <&phy7>;
 	phy-mode = "sgmii";
 	phys = <&serdes 4 SERDES1G(2)>;
 };
 
 &port5 {
+	status = "okay";
 	phy-handle = <&phy4>;
 	phy-mode = "sgmii";
 	phys = <&serdes 5 SERDES1G(5)>;
 };
 
 &port6 {
+	status = "okay";
 	phy-handle = <&phy6>;
 	phy-mode = "sgmii";
 	phys = <&serdes 6 SERDES1G(3)>;
 };
 
 &port9 {
+	status = "okay";
 	phy-handle = <&phy5>;
 	phy-mode = "sgmii";
 	phys = <&serdes 9 SERDES1G(4)>;
diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
index ef852f382da8..7d7e638791dd 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
@@ -47,17 +47,21 @@ &mdio0 {
 };
 
 &port0 {
+	status = "okay";
 	phy-handle = <&phy0>;
 };
 
 &port1 {
+	status = "okay";
 	phy-handle = <&phy1>;
 };
 
 &port2 {
+	status = "okay";
 	phy-handle = <&phy2>;
 };
 
 &port3 {
+	status = "okay";
 	phy-handle = <&phy3>;
 };
-- 
2.30.2

[PATCH AUTOSEL 5.10 31/53] MIPS: mscc: ocelot: mark the phy-mode for internal PHY ports

[Sasha Levin]

From: Vladimir Oltean <vladimir.oltean@nxp.com>

[ Upstream commit eba54cbb92d28b4f6dc1ed5f73f5187b09d82c08 ]

The ocelot driver was converted to phylink, and that expects a valid
phy_interface_t. Without a phy-mode, of_get_phy_mode returns
PHY_INTERFACE_MODE_NA, which is not ideal because phylink rejects that.

The ocelot driver was patched to treat PHY_INTERFACE_MODE_NA as
PHY_INTERFACE_MODE_INTERNAL to work with the broken DT blobs, but we
should fix the device trees and specify the phy-mode too.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/mips/boot/dts/mscc/ocelot_pcb120.dts | 4 ++++
 arch/mips/boot/dts/mscc/ocelot_pcb123.dts | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb120.dts b/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
index d2dc6b3d923c..bd240690cb37 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb120.dts
@@ -71,21 +71,25 @@ phy4: ethernet-phy@3 {
 &port0 {
 	status = "okay";
 	phy-handle = <&phy0>;
+	phy-mode = "internal";
 };
 
 &port1 {
 	status = "okay";
 	phy-handle = <&phy1>;
+	phy-mode = "internal";
 };
 
 &port2 {
 	status = "okay";
 	phy-handle = <&phy2>;
+	phy-mode = "internal";
 };
 
 &port3 {
 	status = "okay";
 	phy-handle = <&phy3>;
+	phy-mode = "internal";
 };
 
 &port4 {
diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
index 7d7e638791dd..0185045c7630 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
@@ -49,19 +49,23 @@ &mdio0 {
 &port0 {
 	status = "okay";
 	phy-handle = <&phy0>;
+	phy-mode = "internal";
 };
 
 &port1 {
 	status = "okay";
 	phy-handle = <&phy1>;
+	phy-mode = "internal";
 };
 
 &port2 {
 	status = "okay";
 	phy-handle = <&phy2>;
+	phy-mode = "internal";
 };
 
 &port3 {
 	status = "okay";
 	phy-handle = <&phy3>;
+	phy-mode = "internal";
 };
-- 
2.30.2

[PATCH AUTOSEL 5.10 32/53] scsi: qla2xxx: Fix NVMe | FCP personality change

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit f6e327fc09e48271c103efb3b69fc4ccda3f408b ]

Currently driver saves the personality type (FCP|NVMe) at the start of
first discovery of the remote device. If the remote device personality do
change over time, then qla driver needs to present that to user to decide.

Link: https://lore.kernel.org/r/20210817051315.2477-8-njavali@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_gs.c   | 1 +
 drivers/scsi/qla2xxx/qla_init.c | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index e28c4b7ec55f..eddf3335e4e3 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -3494,6 +3494,7 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 				continue;
 			fcport->scan_state = QLA_FCPORT_FOUND;
 			fcport->last_rscn_gen = fcport->rscn_gen;
+			fcport->fc4_type = rp->fc4type;
 			found = true;
 			/*
 			 * If device was not a fabric device before.
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index d3526a247841..1a81f3b721b6 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1533,11 +1533,12 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 	u16 sec;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d8,
-	    "%s %8phC DS %d LS %d P %d fl %x confl %p rscn %d|%d login %d lid %d scan %d\n",
+	    "%s %8phC DS %d LS %d P %d fl %x confl %p rscn %d|%d login %d lid %d scan %d fc4type %x\n",
 	    __func__, fcport->port_name, fcport->disc_state,
 	    fcport->fw_login_state, fcport->login_pause, fcport->flags,
 	    fcport->conflict, fcport->last_rscn_gen, fcport->rscn_gen,
-	    fcport->login_gen, fcport->loop_id, fcport->scan_state);
+	    fcport->login_gen, fcport->loop_id, fcport->scan_state,
+	    fcport->fc4_type);
 
 	if (fcport->scan_state != QLA_FCPORT_FOUND)
 		return 0;
-- 
2.30.2

[PATCH AUTOSEL 5.10 33/53] scsi: qla2xxx: Fix NVMe session down detection

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit 7a8ff7d9854a1727435557184c8255bbbca60920 ]

When Target port transitions personality from one to another (NVMe <-->
FCP), there could be some overlap of the two where one layer is going down
while the other layer is coming up. This overlap can cause temporary I/O
error. Detect those errors/transitions and recover from them. Triggers
session tear down and allow relogin to re-drive the connection under the
following conditions:

 - NVMe command error

 - On PRLO + N2N (rida format 2)

Link: https://lore.kernel.org/r/20210817051315.2477-11-njavali@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_attr.c | 12 +++++++-----
 drivers/scsi/qla2xxx/qla_isr.c  |  9 +++++++++
 drivers/scsi/qla2xxx/qla_mbx.c  | 10 ++++++++++
 3 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 6a2c4a6fcded..22f230e001cc 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2700,12 +2700,14 @@ qla2x00_terminate_rport_io(struct fc_rport *rport)
 	 * final cleanup of firmware resources (PCBs and XCBs).
 	 */
 	if (fcport->loop_id != FC_NO_LOOP_ID) {
-		if (IS_FWI2_CAPABLE(fcport->vha->hw))
-			fcport->vha->hw->isp_ops->fabric_logout(fcport->vha,
-			    fcport->loop_id, fcport->d_id.b.domain,
-			    fcport->d_id.b.area, fcport->d_id.b.al_pa);
-		else
+		if (IS_FWI2_CAPABLE(fcport->vha->hw)) {
+			if (fcport->loop_id != FC_NO_LOOP_ID)
+				fcport->logout_on_delete = 1;
+
+			qlt_schedule_sess_for_deletion(fcport);
+		} else {
 			qla2x00_port_logout(fcport->vha, fcport);
+		}
 	}
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index a24b82de4aab..db4182ecbc26 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2380,6 +2380,15 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	case CS_PORT_UNAVAILABLE:
 	case CS_PORT_LOGGED_OUT:
 		fcport->nvme_flag |= NVME_FLAG_RESETTING;
+		if (atomic_read(&fcport->state) == FCS_ONLINE) {
+			ql_dbg(ql_dbg_disc, fcport->vha, 0x3021,
+			       "Port to be marked lost on fcport=%06x, current "
+			       "port state= %s comp_status %x.\n",
+			       fcport->d_id.b24, port_state_str[FCS_ONLINE],
+			       comp_status);
+
+			qlt_schedule_sess_for_deletion(fcport);
+		}
 		fallthrough;
 	case CS_ABORTED:
 	case CS_PORT_BUSY:
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 4ebd8851a0c9..91c3bd7829de 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -4136,6 +4136,16 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 				rptid_entry->u.f2.remote_nport_id[1];
 			fcport->d_id.b.al_pa =
 				rptid_entry->u.f2.remote_nport_id[0];
+
+			/*
+			 * For the case where remote port sending PRLO, FW
+			 * sends up RIDA Format 2 as an indication of session
+			 * loss. In other word, FW state change from PRLI
+			 * complete back to PLOGI complete. Delete the
+			 * session and let relogin drive the reconnect.
+			 */
+			if (atomic_read(&fcport->state) == FCS_ONLINE)
+				qlt_schedule_sess_for_deletion(fcport);
 		}
 	}
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 34/53] scsi: core: Fix missing FORCE for scsi_devinfo_tbl.c build rule

[Sasha Levin]

From: Masahiro Yamada <masahiroy@kernel.org>

[ Upstream commit 98079418c53fff5f9e2d4087f08eaff2a9ce7714 ]

Add FORCE so that if_changed can detect the command line change.
scsi_devinfo_tbl.c must be added to 'targets' too.

Link: https://lore.kernel.org/r/20210819012339.709409-1-masahiroy@kernel.org
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/Makefile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index c00e3dd57990..7ac42eaa6250 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -183,7 +183,7 @@ CFLAGS_ncr53c8xx.o	:= $(ncr53c8xx-flags-y) $(ncr53c8xx-flags-m)
 zalon7xx-objs	:= zalon.o ncr53c8xx.o
 
 # Files generated that shall be removed upon make clean
-clean-files :=	53c700_d.h 53c700_u.h scsi_devinfo_tbl.c
+clean-files :=	53c700_d.h 53c700_u.h
 
 $(obj)/53c700.o: $(obj)/53c700_d.h
 
@@ -192,9 +192,11 @@ $(obj)/scsi_sysfs.o: $(obj)/scsi_devinfo_tbl.c
 quiet_cmd_bflags = GEN     $@
 	cmd_bflags = sed -n 's/.*define *BLIST_\([A-Z0-9_]*\) *.*/BLIST_FLAG_NAME(\1),/p' $< > $@
 
-$(obj)/scsi_devinfo_tbl.c: include/scsi/scsi_devinfo.h
+$(obj)/scsi_devinfo_tbl.c: include/scsi/scsi_devinfo.h FORCE
 	$(call if_changed,bflags)
 
+targets +=  scsi_devinfo_tbl.c
+
 # If you want to play with the firmware, uncomment
 # GENERATE_FIRMWARE := 1
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 35/53] powerpc/32: indirect function call use bctrl rather than blrl in ret_from_kernel_thread

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 113ec9ccc8049c3772f0eab46b62c5d6654c09f7 ]

Copied from commit 89bbe4c798bc ("powerpc/64: indirect function call
use bctrl rather than blrl in ret_from_kernel_thread")

blrl is not recommended to use as an indirect function call, as it may
corrupt the link stack predictor.

This is not a performance critical path but this should be fixed for
consistency.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/91b1d242525307ceceec7ef6e832bfbacdd4501b.1629436472.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/entry_32.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 459f5d00b990..a3db3748172c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -496,10 +496,10 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	mtlr	r14
+	mtctr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
-	blrl
+	bctrl
 	li	r3,0
 	b	ret_from_syscall
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 35/53] powerpc/32: indirect function call use bctrl rather than blrl in ret_from_kernel_thread

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 113ec9ccc8049c3772f0eab46b62c5d6654c09f7 ]

Copied from commit 89bbe4c798bc ("powerpc/64: indirect function call
use bctrl rather than blrl in ret_from_kernel_thread")

blrl is not recommended to use as an indirect function call, as it may
corrupt the link stack predictor.

This is not a performance critical path but this should be fixed for
consistency.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/91b1d242525307ceceec7ef6e832bfbacdd4501b.1629436472.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/entry_32.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 459f5d00b990..a3db3748172c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -496,10 +496,10 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	mtlr	r14
+	mtctr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
-	blrl
+	bctrl
 	li	r3,0
 	b	ret_from_syscall
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 36/53] powerpc/booke: Avoid link stack corruption in several places

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit f5007dbf4da729baa850b33a64dc3cc53757bdf8 ]

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/e9fbc285eceb720e6c0e032ef47fe8b05f669b48.1629791751.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/ppc_asm.h            | 2 +-
 arch/powerpc/kernel/exceptions-64e.S          | 6 +++---
 arch/powerpc/kernel/fsl_booke_entry_mapping.S | 8 ++++----
 arch/powerpc/kernel/head_44x.S                | 6 +++---
 arch/powerpc/kernel/head_fsl_booke.S          | 6 +++---
 arch/powerpc/mm/nohash/tlb_low.S              | 4 ++--
 6 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 511786f0e40d..f42ba0b86a3a 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -306,7 +306,7 @@ GLUE(.,name):
 
 /* Be careful, this will clobber the lr register. */
 #define LOAD_REG_ADDR_PIC(reg, name)		\
-	bl	0f;				\
+	bcl	20,31,$+4;			\
 0:	mflr	reg;				\
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index f579ce46eef2..1bb505eeb154 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1443,7 +1443,7 @@ found_iprot:
  * r3 = MAS0_TLBSEL (for the iprot array)
  * r4 = SPRN_TLBnCFG
  */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r5,r7,27,31,31			/* extract MSR[IS] */
@@ -1512,7 +1512,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mfmsr	r6
 	xori	r6,r6,MSR_IS
 	mtspr	SPRN_SRR1,r6
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
@@ -1572,7 +1572,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
  * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
  */
 	/* Now we branch the new virtual address mapped by this entry */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	tovirt(r6,r6)
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index 8bccce6544b5..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /* 1. Find the index of the entry we're executing in */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r4,r7,27,31,31			/* extract MSR[IS] */
@@ -85,7 +85,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	addi	r6,r6,10
 	slw	r6,r8,r6	/* convert to mask */
 
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r7
 
 	mfspr	r8,SPRN_MAS3
@@ -117,7 +117,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 	xori	r6,r4,1
 	slwi	r6,r6,5		/* setup new context with other address space */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
 	addi	r7,r7,(2f - 1b)
@@ -207,7 +207,7 @@ next_tlb_setup:
 
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
-	bl	1f			/* Find our address */
+	bcl	20,31,$+4		/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 8e36718f3167..b178b372e66e 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -70,7 +70,7 @@ _ENTRY(_start);
  * address.
  * r21 will be loaded with the physical runtime address of _stext
  */
-	bl	0f				/* Get our runtime address */
+	bcl	20,31,$+4			/* Get our runtime address */
 0:	mflr	r21				/* Make it accessible */
 	addis	r21,r21,(_stext - 0b)@ha
 	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
@@ -861,7 +861,7 @@ _GLOBAL(init_cpu_state)
 wmmucr:	mtspr	SPRN_MMUCR,r3			/* Put MMUCR */
 	sync
 
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -1053,7 +1053,7 @@ head_start_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r23
 	tlbsx	r23,0,r23
 	tlbre	r24,r23,0
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 586a6ac501e9..daf4a72bb08f 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -79,7 +79,7 @@ _ENTRY(_start);
 	mr	r23,r3
 	mr	r25,r4
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r8
 	addis	r3,r8,(is_second_reloc - 0b)@ha
 	lwz	r19,(is_second_reloc - 0b)@l(r3)
@@ -1195,7 +1195,7 @@ _GLOBAL(switch_to_as1)
 	bne	1b
 
 	/* Get the tlb entry used by the current running code */
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r4
 	tlbsx	0,r4
 
@@ -1229,7 +1229,7 @@ _GLOBAL(switch_to_as1)
 _GLOBAL(restore_to_as0)
 	mflr	r0
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r9
 	addi	r9,r9,1f - 0b
 
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index eaeee402f96e..f849f26bfbfb 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -214,7 +214,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2)
  * Touch enough instruction cache lines to ensure cache hits
  */
 1:	mflr	r9
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r6
 	li	r7,32
 	PPC_ICBT(0,R6,R7)		/* touch next cache line */
@@ -442,7 +442,7 @@ _GLOBAL(loadcam_multi)
 	 * Set up temporary TLB entry that is the same as what we're
 	 * running from, but in AS=1.
 	 */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	tlbsx	0,r8
 	mfspr	r6,SPRN_MAS1
-- 
2.30.2

[PATCH AUTOSEL 5.10 36/53] powerpc/booke: Avoid link stack corruption in several places

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit f5007dbf4da729baa850b33a64dc3cc53757bdf8 ]

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/e9fbc285eceb720e6c0e032ef47fe8b05f669b48.1629791751.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/ppc_asm.h            | 2 +-
 arch/powerpc/kernel/exceptions-64e.S          | 6 +++---
 arch/powerpc/kernel/fsl_booke_entry_mapping.S | 8 ++++----
 arch/powerpc/kernel/head_44x.S                | 6 +++---
 arch/powerpc/kernel/head_fsl_booke.S          | 6 +++---
 arch/powerpc/mm/nohash/tlb_low.S              | 4 ++--
 6 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 511786f0e40d..f42ba0b86a3a 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -306,7 +306,7 @@ GLUE(.,name):
 
 /* Be careful, this will clobber the lr register. */
 #define LOAD_REG_ADDR_PIC(reg, name)		\
-	bl	0f;				\
+	bcl	20,31,$+4;			\
 0:	mflr	reg;				\
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index f579ce46eef2..1bb505eeb154 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1443,7 +1443,7 @@ found_iprot:
  * r3 = MAS0_TLBSEL (for the iprot array)
  * r4 = SPRN_TLBnCFG
  */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r5,r7,27,31,31			/* extract MSR[IS] */
@@ -1512,7 +1512,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mfmsr	r6
 	xori	r6,r6,MSR_IS
 	mtspr	SPRN_SRR1,r6
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
@@ -1572,7 +1572,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
  * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
  */
 	/* Now we branch the new virtual address mapped by this entry */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	tovirt(r6,r6)
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index 8bccce6544b5..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /* 1. Find the index of the entry we're executing in */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r4,r7,27,31,31			/* extract MSR[IS] */
@@ -85,7 +85,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	addi	r6,r6,10
 	slw	r6,r8,r6	/* convert to mask */
 
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r7
 
 	mfspr	r8,SPRN_MAS3
@@ -117,7 +117,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 	xori	r6,r4,1
 	slwi	r6,r6,5		/* setup new context with other address space */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
 	addi	r7,r7,(2f - 1b)
@@ -207,7 +207,7 @@ next_tlb_setup:
 
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
-	bl	1f			/* Find our address */
+	bcl	20,31,$+4		/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 8e36718f3167..b178b372e66e 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -70,7 +70,7 @@ _ENTRY(_start);
  * address.
  * r21 will be loaded with the physical runtime address of _stext
  */
-	bl	0f				/* Get our runtime address */
+	bcl	20,31,$+4			/* Get our runtime address */
 0:	mflr	r21				/* Make it accessible */
 	addis	r21,r21,(_stext - 0b)@ha
 	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
@@ -861,7 +861,7 @@ _GLOBAL(init_cpu_state)
 wmmucr:	mtspr	SPRN_MMUCR,r3			/* Put MMUCR */
 	sync
 
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -1053,7 +1053,7 @@ head_start_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r23
 	tlbsx	r23,0,r23
 	tlbre	r24,r23,0
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 586a6ac501e9..daf4a72bb08f 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -79,7 +79,7 @@ _ENTRY(_start);
 	mr	r23,r3
 	mr	r25,r4
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r8
 	addis	r3,r8,(is_second_reloc - 0b)@ha
 	lwz	r19,(is_second_reloc - 0b)@l(r3)
@@ -1195,7 +1195,7 @@ _GLOBAL(switch_to_as1)
 	bne	1b
 
 	/* Get the tlb entry used by the current running code */
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r4
 	tlbsx	0,r4
 
@@ -1229,7 +1229,7 @@ _GLOBAL(switch_to_as1)
 _GLOBAL(restore_to_as0)
 	mflr	r0
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r9
 	addi	r9,r9,1f - 0b
 
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index eaeee402f96e..f849f26bfbfb 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -214,7 +214,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2)
  * Touch enough instruction cache lines to ensure cache hits
  */
 1:	mflr	r9
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r6
 	li	r7,32
 	PPC_ICBT(0,R6,R7)		/* touch next cache line */
@@ -442,7 +442,7 @@ _GLOBAL(loadcam_multi)
 	 * Set up temporary TLB entry that is the same as what we're
 	 * running from, but in AS=1.
 	 */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	tlbsx	0,r8
 	mfspr	r6,SPRN_MAS1
-- 
2.30.2

[PATCH AUTOSEL 5.10 37/53] powerpc: Avoid link stack corruption in misc asm functions

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 33e1402435cb9f3021439a15935ea2dc69ec1844 ]

bl;mflr is used at several places to get code position.

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c6eabb4fb6c156f75d56dcbcc6f243e5ac0fba42.1629791763.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/misc.S       |  2 +-
 arch/powerpc/kernel/misc_32.S    |  2 +-
 arch/powerpc/kernel/misc_64.S    |  2 +-
 arch/powerpc/kernel/reloc_32.S   |  2 +-
 arch/powerpc/kexec/relocate_32.S | 12 ++++++------
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 5be96feccb55..fb7de3543c03 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -29,7 +29,7 @@ _GLOBAL(reloc_offset)
 	li	r3, 0
 _GLOBAL(add_reloc_offset)
 	mflr	r0
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 717e658b90fd..9511f077842b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -106,7 +106,7 @@ _GLOBAL(reloc_got2)
 	srwi.	r8,r8,2
 	beqlr
 	mtctr	r8
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r0
 	lis	r4,1b@ha
 	addi	r4,r4,1b@l
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 070465825c21..81870c1c827f 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -277,7 +277,7 @@ _GLOBAL(scom970_write)
  * Physical (hardware) cpu id should be in r3.
  */
 _GLOBAL(kexec_wait)
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index 10e96f3e22fe..0508c14b4c28 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -30,7 +30,7 @@ R_PPC_RELATIVE = 22
 _GLOBAL(relocate)
 
 	mflr	r0		/* Save our LR */
-	bl	0f		/* Find our current runtime address */
+	bcl	20,31,$+4	/* Find our current runtime address */
 0:	mflr	r12		/* Make it accessible */
 	mtlr	r0
 
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index 61946c19e07c..cf6e52bdf8d8 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -93,7 +93,7 @@ wmmucr:
 	 * Invalidate all the TLB entries except the current entry
 	 * where we are running from
 	 */
-	bl	0f				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 0:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -158,7 +158,7 @@ write_out:
 	/* Switch to other address space in MSR */
 	insrwi	r9, r7, 1, 26		/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	addi	r8, r8, (2f-1b)		/* Find the target offset */
 
@@ -202,7 +202,7 @@ next_tlb:
 	li	r9,0
 	insrwi	r9, r7, 1, 26			/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	and	r8, r8, r11			/* Get our offset within page */
 	addi	r8, r8, (2f-1b)
@@ -240,7 +240,7 @@ setup_map_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r23
 	tlbsx	r23, 0, r23
 	tlbre	r24, r23, 0			/* TLB Word 0 */
@@ -296,7 +296,7 @@ clear_utlb_entry:
 	/* Update the msr to the new TS */
 	insrwi	r5, r7, 1, 26
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	addi	r6, r6, (2f-1b)
 
@@ -355,7 +355,7 @@ write_utlb:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 37/53] powerpc: Avoid link stack corruption in misc asm functions

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 33e1402435cb9f3021439a15935ea2dc69ec1844 ]

bl;mflr is used at several places to get code position.

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c6eabb4fb6c156f75d56dcbcc6f243e5ac0fba42.1629791763.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/misc.S       |  2 +-
 arch/powerpc/kernel/misc_32.S    |  2 +-
 arch/powerpc/kernel/misc_64.S    |  2 +-
 arch/powerpc/kernel/reloc_32.S   |  2 +-
 arch/powerpc/kexec/relocate_32.S | 12 ++++++------
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 5be96feccb55..fb7de3543c03 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -29,7 +29,7 @@ _GLOBAL(reloc_offset)
 	li	r3, 0
 _GLOBAL(add_reloc_offset)
 	mflr	r0
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 717e658b90fd..9511f077842b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -106,7 +106,7 @@ _GLOBAL(reloc_got2)
 	srwi.	r8,r8,2
 	beqlr
 	mtctr	r8
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r0
 	lis	r4,1b@ha
 	addi	r4,r4,1b@l
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 070465825c21..81870c1c827f 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -277,7 +277,7 @@ _GLOBAL(scom970_write)
  * Physical (hardware) cpu id should be in r3.
  */
 _GLOBAL(kexec_wait)
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index 10e96f3e22fe..0508c14b4c28 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -30,7 +30,7 @@ R_PPC_RELATIVE = 22
 _GLOBAL(relocate)
 
 	mflr	r0		/* Save our LR */
-	bl	0f		/* Find our current runtime address */
+	bcl	20,31,$+4	/* Find our current runtime address */
 0:	mflr	r12		/* Make it accessible */
 	mtlr	r0
 
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index 61946c19e07c..cf6e52bdf8d8 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -93,7 +93,7 @@ wmmucr:
 	 * Invalidate all the TLB entries except the current entry
 	 * where we are running from
 	 */
-	bl	0f				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 0:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -158,7 +158,7 @@ write_out:
 	/* Switch to other address space in MSR */
 	insrwi	r9, r7, 1, 26		/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	addi	r8, r8, (2f-1b)		/* Find the target offset */
 
@@ -202,7 +202,7 @@ next_tlb:
 	li	r9,0
 	insrwi	r9, r7, 1, 26			/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	and	r8, r8, r11			/* Get our offset within page */
 	addi	r8, r8, (2f-1b)
@@ -240,7 +240,7 @@ setup_map_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r23
 	tlbsx	r23, 0, r23
 	tlbre	r24, r23, 0			/* TLB Word 0 */
@@ -296,7 +296,7 @@ clear_utlb_entry:
 	/* Update the msr to the new TS */
 	insrwi	r5, r7, 1, 26
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	addi	r6, r6, (2f-1b)
 
@@ -355,7 +355,7 @@ write_utlb:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 38/53] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit fd42b7b09c602c904452c0c3e5955ca21d8e387a ]

It is possible to create a VCPU without setting the MSR before running
it, which results in a warning in kvmhv_vcpu_entry_p9() that MSR_ME is
not set. This is pretty harmless because the MSR_ME bit is added to
HSRR1 before HRFID to guest, and a normal qemu guest doesn't hit it.

Initialise the vcpu MSR with MSR_ME set.

Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bd7350a608d4..8e16dfecbe36 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2353,6 +2353,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.shregs.msr = MSR_ME;
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
-- 
2.30.2

[PATCH AUTOSEL 5.10 38/53] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit fd42b7b09c602c904452c0c3e5955ca21d8e387a ]

It is possible to create a VCPU without setting the MSR before running
it, which results in a warning in kvmhv_vcpu_entry_p9() that MSR_ME is
not set. This is pretty harmless because the MSR_ME bit is added to
HSRR1 before HRFID to guest, and a normal qemu guest doesn't hit it.

Initialise the vcpu MSR with MSR_ME set.

Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bd7350a608d4..8e16dfecbe36 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2353,6 +2353,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.shregs.msr = MSR_ME;
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
-- 
2.30.2

[PATCH AUTOSEL 5.10 38/53] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit fd42b7b09c602c904452c0c3e5955ca21d8e387a ]

It is possible to create a VCPU without setting the MSR before running
it, which results in a warning in kvmhv_vcpu_entry_p9() that MSR_ME is
not set. This is pretty harmless because the MSR_ME bit is added to
HSRR1 before HRFID to guest, and a normal qemu guest doesn't hit it.

Initialise the vcpu MSR with MSR_ME set.

Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bd7350a608d4..8e16dfecbe36 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2353,6 +2353,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.shregs.msr = MSR_ME;
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
-- 
2.30.2

[PATCH AUTOSEL 5.10 39/53] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 4782e0cd0d184d727ad3b0cfe20d1d44d9f98239 ]

The softpatch interrupt sets HSRR0 to the faulting instruction +4, so
it should subtract 4 for the faulting instruction address in the case
it is a TM softpatch interrupt (the instruction was not executed) and
it was not emulated.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-4-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv_tm.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..e7c36f8bf205 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
+	/*
+	 * The TM softpatch interrupt sets NIP to the instruction following
+	 * the faulting instruction, which is not executed. Rewind nip to the
+	 * faulting instruction so it looks like a normal synchronous
+	 * interrupt, then update nip in the places where the instruction is
+	 * emulated.
+	 */
+	vcpu->arch.regs.nip -= 4;
+
 	/*
 	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
 	 * in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
@@ -100,7 +109,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
@@ -116,6 +125,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -152,6 +162,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
 		}
 		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -189,6 +200,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -220,6 +232,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 39/53] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 4782e0cd0d184d727ad3b0cfe20d1d44d9f98239 ]

The softpatch interrupt sets HSRR0 to the faulting instruction +4, so
it should subtract 4 for the faulting instruction address in the case
it is a TM softpatch interrupt (the instruction was not executed) and
it was not emulated.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-4-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv_tm.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..e7c36f8bf205 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
+	/*
+	 * The TM softpatch interrupt sets NIP to the instruction following
+	 * the faulting instruction, which is not executed. Rewind nip to the
+	 * faulting instruction so it looks like a normal synchronous
+	 * interrupt, then update nip in the places where the instruction is
+	 * emulated.
+	 */
+	vcpu->arch.regs.nip -= 4;
+
 	/*
 	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
 	 * in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
@@ -100,7 +109,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
@@ -116,6 +125,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -152,6 +162,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
 		}
 		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -189,6 +200,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -220,6 +232,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 39/53] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 4782e0cd0d184d727ad3b0cfe20d1d44d9f98239 ]

The softpatch interrupt sets HSRR0 to the faulting instruction +4, so
it should subtract 4 for the faulting instruction address in the case
it is a TM softpatch interrupt (the instruction was not executed) and
it was not emulated.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-4-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv_tm.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..e7c36f8bf205 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
+	/*
+	 * The TM softpatch interrupt sets NIP to the instruction following
+	 * the faulting instruction, which is not executed. Rewind nip to the
+	 * faulting instruction so it looks like a normal synchronous
+	 * interrupt, then update nip in the places where the instruction is
+	 * emulated.
+	 */
+	vcpu->arch.regs.nip -= 4;
+
 	/*
 	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
 	 * in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
@@ -100,7 +109,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
@@ -116,6 +125,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -152,6 +162,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
 		}
 		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -189,6 +200,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -220,6 +232,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 40/53] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit d82b392d9b3556b63e3f9916cf057ea847e173a9 ]

Have the TM softpatch emulation code set up the HFAC interrupt and
return -1 in case an instruction was executed with HFSCR bits clear,
and have the interrupt exit handler fall through to the HFAC handler.
When the L0 is running a nested guest, this ensures the HFAC interrupt
is correctly passed up to the L1.

The "direct guest" exit handler will turn these into PROGILL program
interrupts so functionality in practice will be unchanged. But it's
possible an L1 would want to handle these in a different way.

Also rearrange the FAC interrupt emulation code to match the HFAC format
while here (mainly, adding the FSCR_INTR_CAUSE mask).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-5-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/reg.h  |  3 ++-
 arch/powerpc/kvm/book3s_hv.c    | 35 ++++++++++++++++----------
 arch/powerpc/kvm/book3s_hv_tm.c | 44 ++++++++++++++++++---------------
 3 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f4b98903064f..af07347ac61a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -417,6 +417,7 @@
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
@@ -428,7 +429,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
-#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
+#define   HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8e16dfecbe36..c63fb61de62a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1425,6 +1425,21 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
+#endif
+
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
 	 * is prohibited by HFSCR.
@@ -1443,18 +1458,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
-		/*
-		 * This occurs for various TM-related instructions that
-		 * we need to emulate on POWER9 DD2.2.  We have already
-		 * handled the cases where the guest was in real-suspend
-		 * mode and was transitioning to transactional state.
-		 */
-		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
-#endif
-
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
@@ -1552,9 +1555,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * mode and was transitioning to transactional state.
 		 */
 		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
 #endif
 
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
+		break;
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
 		r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index e7c36f8bf205..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -88,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check EBB facility is available */
 		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_EBB_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
 		}
@@ -138,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -169,14 +171,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -208,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
-- 
2.30.2

[PATCH AUTOSEL 5.10 40/53] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit d82b392d9b3556b63e3f9916cf057ea847e173a9 ]

Have the TM softpatch emulation code set up the HFAC interrupt and
return -1 in case an instruction was executed with HFSCR bits clear,
and have the interrupt exit handler fall through to the HFAC handler.
When the L0 is running a nested guest, this ensures the HFAC interrupt
is correctly passed up to the L1.

The "direct guest" exit handler will turn these into PROGILL program
interrupts so functionality in practice will be unchanged. But it's
possible an L1 would want to handle these in a different way.

Also rearrange the FAC interrupt emulation code to match the HFAC format
while here (mainly, adding the FSCR_INTR_CAUSE mask).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-5-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/reg.h  |  3 ++-
 arch/powerpc/kvm/book3s_hv.c    | 35 ++++++++++++++++----------
 arch/powerpc/kvm/book3s_hv_tm.c | 44 ++++++++++++++++++---------------
 3 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f4b98903064f..af07347ac61a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -417,6 +417,7 @@
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
@@ -428,7 +429,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
-#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
+#define   HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8e16dfecbe36..c63fb61de62a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1425,6 +1425,21 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
+#endif
+
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
 	 * is prohibited by HFSCR.
@@ -1443,18 +1458,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
-		/*
-		 * This occurs for various TM-related instructions that
-		 * we need to emulate on POWER9 DD2.2.  We have already
-		 * handled the cases where the guest was in real-suspend
-		 * mode and was transitioning to transactional state.
-		 */
-		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
-#endif
-
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
@@ -1552,9 +1555,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * mode and was transitioning to transactional state.
 		 */
 		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
 #endif
 
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
+		break;
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
 		r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index e7c36f8bf205..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -88,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check EBB facility is available */
 		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_EBB_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
 		}
@@ -138,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -169,14 +171,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -208,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
-- 
2.30.2

[PATCH AUTOSEL 5.10 40/53] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit d82b392d9b3556b63e3f9916cf057ea847e173a9 ]

Have the TM softpatch emulation code set up the HFAC interrupt and
return -1 in case an instruction was executed with HFSCR bits clear,
and have the interrupt exit handler fall through to the HFAC handler.
When the L0 is running a nested guest, this ensures the HFAC interrupt
is correctly passed up to the L1.

The "direct guest" exit handler will turn these into PROGILL program
interrupts so functionality in practice will be unchanged. But it's
possible an L1 would want to handle these in a different way.

Also rearrange the FAC interrupt emulation code to match the HFAC format
while here (mainly, adding the FSCR_INTR_CAUSE mask).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-5-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/reg.h  |  3 ++-
 arch/powerpc/kvm/book3s_hv.c    | 35 ++++++++++++++++----------
 arch/powerpc/kvm/book3s_hv_tm.c | 44 ++++++++++++++++++---------------
 3 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f4b98903064f..af07347ac61a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -417,6 +417,7 @@
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
@@ -428,7 +429,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
-#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
+#define   HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8e16dfecbe36..c63fb61de62a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1425,6 +1425,21 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
+#endif
+
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
 	 * is prohibited by HFSCR.
@@ -1443,18 +1458,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
-		/*
-		 * This occurs for various TM-related instructions that
-		 * we need to emulate on POWER9 DD2.2.  We have already
-		 * handled the cases where the guest was in real-suspend
-		 * mode and was transitioning to transactional state.
-		 */
-		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
-#endif
-
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
@@ -1552,9 +1555,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * mode and was transitioning to transactional state.
 		 */
 		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
 #endif
 
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
+		break;
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
 		r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index e7c36f8bf205..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -88,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check EBB facility is available */
 		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_EBB_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
 		}
@@ -138,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -169,14 +171,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -208,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
-- 
2.30.2

[PATCH AUTOSEL 5.10 41/53] RDMA/core/sa_query: Retry SA queries

[Sasha Levin]

From: Håkon Bugge <haakon.bugge@oracle.com>

[ Upstream commit 5f5a650999d5718af766fc70a120230b04235a6f ]

A MAD packet is sent as an unreliable datagram (UD). SA requests are sent
as MAD packets. As such, SA requests or responses may be silently dropped.

IB Core's MAD layer has a timeout and retry mechanism, which amongst
other, is used by RDMA CM. But it is not used by SA queries. The lack of
retries of SA queries leads to long specified timeout, and error being
returned in case of packet loss. The ULP or user-land process has to
perform the retry.

Fix this by taking advantage of the MAD layer's retry mechanism.

First, a check against a zero timeout is added in rdma_resolve_route(). In
send_mad(), we set the MAD layer timeout to one tenth of the specified
timeout and the number of retries to 10. The special case when timeout is
less than 10 is handled.

With this fix:

 # ucmatose -c 1000 -S 1024 -C 1

runs stable on an Infiniband fabric. Without this fix, we see an
intermittent behavior and it errors out with:

cmatose: event: RDMA_CM_EVENT_ROUTE_ERROR, error: -110

(110 is ETIMEDOUT)

Link: https://lore.kernel.org/r/1628784755-28316-1-git-send-email-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/core/cma.c      | 3 +++
 drivers/infiniband/core/sa_query.c | 9 ++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 34b94e525390..3fef344df3a5 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -3096,6 +3096,9 @@ int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms)
 	struct rdma_id_private *id_priv;
 	int ret;
 
+	if (!timeout_ms)
+		return -EINVAL;
+
 	id_priv = container_of(id, struct rdma_id_private, id);
 	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY))
 		return -EINVAL;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 8c930bf1df89..9f263642e845 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1360,6 +1360,7 @@ static int send_mad(struct ib_sa_query *query, unsigned long timeout_ms,
 {
 	unsigned long flags;
 	int ret, id;
+	const int nmbr_sa_query_retries = 10;
 
 	xa_lock_irqsave(&queries, flags);
 	ret = __xa_alloc(&queries, &id, query, xa_limit_32b, gfp_mask);
@@ -1367,7 +1368,13 @@ static int send_mad(struct ib_sa_query *query, unsigned long timeout_ms,
 	if (ret < 0)
 		return ret;
 
-	query->mad_buf->timeout_ms  = timeout_ms;
+	query->mad_buf->timeout_ms  = timeout_ms / nmbr_sa_query_retries;
+	query->mad_buf->retries = nmbr_sa_query_retries;
+	if (!query->mad_buf->timeout_ms) {
+		/* Special case, very small timeout_ms */
+		query->mad_buf->timeout_ms = 1;
+		query->mad_buf->retries = timeout_ms;
+	}
 	query->mad_buf->context[0] = query;
 	query->id = id;
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 42/53] selftests: openat2: Fix testing failure for O_LARGEFILE flag

[Sasha Levin]

From: Baolin Wang <baolin.wang@linux.alibaba.com>

[ Upstream commit d538ddb97e066571e4fc58b832f40739621b42bb ]

The openat2 test suite fails on ARM64 because the definition of
O_LARGEFILE is different on ARM64. Fix the problem by defining
the correct O_LARGEFILE definition on ARM64.

"openat2 unexpectedly returned # 3['.../tools/testing/selftests/openat2']
with 208000 (!= 208000)
not ok 102 openat2 with incompatible flags (O_PATH | O_LARGEFILE) fails
with -22 (Invalid argument)"

Fixed change log to improve formatting and clarity:
Shuah Khan <skhan@linuxfoundation.org>

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/openat2/openat2_test.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index b386367c606b..5354cef55c6c 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -22,7 +22,11 @@
  * XXX: This is wrong on {mips, parisc, powerpc, sparc}.
  */
 #undef	O_LARGEFILE
+#ifdef __aarch64__
+#define	O_LARGEFILE 0x20000
+#else
 #define	O_LARGEFILE 0x8000
+#endif
 
 struct open_how_ext {
 	struct open_how inner;
-- 
2.30.2

[PATCH AUTOSEL 5.10 43/53] selftests/x86: Fix error: variably modified 'altstack_data' at file scope

[Sasha Levin]

From: Jun Miao <jun.miao@windriver.com>

[ Upstream commit a051b2e56f2aa287b37ab0134a8af852f84e3f8e ]

A glibc 2.34 feature adds support for variable MINSIGSTKSZ and SIGSTKSZ.
When _DYNAMIC_STACK_SIZE_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ
and SIGSTKSZ are no longer constant on Linux. glibc 2.34 flags code paths
assuming MINSIGSTKSZ or SIGSTKSZ are constant. Fix these error in x86 test.

Feature description and build error:

NEWS for version 2.34
=====================
Major new features:
 * Add _SC_MINSIGSTKSZ and _SC_SIGSTKSZ.  When _DYNAMIC_STACK_SIZE_SOURCE
   or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are no longer
   constant on Linux.  MINSIGSTKSZ is redefined to sysconf(_SC_MINSIGSTKSZ)
   and SIGSTKSZ is redefined to sysconf (_SC_SIGSTKSZ).  This supports
   dynamic sized register sets for modern architectural features like
   Arm SVE.
=====================

If _SC_SIGSTKSZ_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ
are redefined as:

/* Default stack size for a signal handler: sysconf (SC_SIGSTKSZ).  */
 # undef SIGSTKSZ
 # define SIGSTKSZ sysconf (_SC_SIGSTKSZ)

/* Minimum stack size for a signal handler: SIGSTKSZ.  */
 # undef MINSIGSTKSZ
 # define MINSIGSTKSZ SIGSTKSZ

Compilation will fail if the source assumes constant MINSIGSTKSZ or
SIGSTKSZ.

Build error with the GNU C Library 2.34:
DEBUG:	| sigreturn.c:150:13: error: variably modified 'altstack_data' at file scope
| sigreturn.c:150:13: error: variably modified 'altstack_data' at file scope
DEBUG:	|   150 | static char altstack_data[SIGSTKSZ];
|   150 | static char altstack_data[SIGSTKSZ];
DEBUG:	|       |             ^~~~~~~~~~~~~

DEBUG:  | single_step_syscall.c:60:22: error: variably modified 'altstack_data' at file scope
DEBUG:  |   60 | static unsigned char altstack_data[SIGSTKSZ];
DEBUG:  |      |                      ^~~~~~~~~~~~~

Fixed commit log to improve formatting and clarity:
Shuah Khan <skhan@linuxfoundation.org>

Link: https://sourceware.org/pipermail/libc-alpha/2021-January/121996.html
Link: https://sourceware.org/pipermail/libc-alpha/2021-August/129718.html
Suggested-by: Jianwei Hu <jianwei.hu@windriver.com>
Signed-off-by: Jun Miao <jun.miao@windriver.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/x86/mov_ss_trap.c         | 4 ++--
 tools/testing/selftests/x86/sigreturn.c           | 7 +++----
 tools/testing/selftests/x86/single_step_syscall.c | 4 ++--
 tools/testing/selftests/x86/syscall_arg_fault.c   | 7 +++----
 4 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
index 6da0ac3f0135..cc3de6ff9fba 100644
--- a/tools/testing/selftests/x86/mov_ss_trap.c
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -47,7 +47,6 @@
 unsigned short ss;
 extern unsigned char breakpoint_insn[];
 sigjmp_buf jmpbuf;
-static unsigned char altstack_data[SIGSTKSZ];
 
 static void enable_watchpoint(void)
 {
@@ -250,13 +249,14 @@ int main()
 	if (sigsetjmp(jmpbuf, 1) == 0) {
 		printf("[RUN]\tMOV SS; SYSENTER\n");
 		stack_t stack = {
-			.ss_sp = altstack_data,
+			.ss_sp = malloc(sizeof(char) * SIGSTKSZ),
 			.ss_size = SIGSTKSZ,
 		};
 		if (sigaltstack(&stack, NULL) != 0)
 			err(1, "sigaltstack");
 		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
 		nr = SYS_getpid;
+		free(stack.ss_sp);
 		/* Clear EBP first to make sure we segfault cleanly. */
 		asm volatile ("xorl %%ebp, %%ebp; mov %[ss], %%ss; SYSENTER" : "+a" (nr)
 			      : [ss] "m" (ss) : "flags", "rcx"
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 57c4f67f16ef..5d7961a5f7f6 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -138,9 +138,6 @@ static unsigned short LDT3(int idx)
 	return (idx << 3) | 7;
 }
 
-/* Our sigaltstack scratch space. */
-static char altstack_data[SIGSTKSZ];
-
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -771,7 +768,8 @@ int main()
 	setup_ldt();
 
 	stack_t stack = {
-		.ss_sp = altstack_data,
+		/* Our sigaltstack scratch space. */
+		.ss_sp = malloc(sizeof(char) * SIGSTKSZ),
 		.ss_size = SIGSTKSZ,
 	};
 	if (sigaltstack(&stack, NULL) != 0)
@@ -872,5 +870,6 @@ int main()
 	total_nerrs += test_nonstrict_ss();
 #endif
 
+	free(stack.ss_sp);
 	return total_nerrs ? 1 : 0;
 }
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 120ac741fe44..9a30f443e928 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -57,7 +57,6 @@ static void clearhandler(int sig)
 
 static volatile sig_atomic_t sig_traps, sig_eflags;
 sigjmp_buf jmpbuf;
-static unsigned char altstack_data[SIGSTKSZ];
 
 #ifdef __x86_64__
 # define REG_IP REG_RIP
@@ -210,7 +209,7 @@ int main()
 		unsigned long nr = SYS_getpid;
 		printf("[RUN]\tSet TF and check SYSENTER\n");
 		stack_t stack = {
-			.ss_sp = altstack_data,
+			.ss_sp = malloc(sizeof(char) * SIGSTKSZ),
 			.ss_size = SIGSTKSZ,
 		};
 		if (sigaltstack(&stack, NULL) != 0)
@@ -219,6 +218,7 @@ int main()
 			   SA_RESETHAND | SA_ONSTACK);
 		sethandler(SIGILL, print_and_longjmp, SA_RESETHAND);
 		set_eflags(get_eflags() | X86_EFLAGS_TF);
+		free(stack.ss_sp);
 		/* Clear EBP first to make sure we segfault cleanly. */
 		asm volatile ("xorl %%ebp, %%ebp; SYSENTER" : "+a" (nr) :: "flags", "rcx"
 #ifdef __x86_64__
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
index bff474b5efc6..461fa41a4d02 100644
--- a/tools/testing/selftests/x86/syscall_arg_fault.c
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -17,9 +17,6 @@
 
 #include "helpers.h"
 
-/* Our sigaltstack scratch space. */
-static unsigned char altstack_data[SIGSTKSZ];
-
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -104,7 +101,8 @@ static void sigill(int sig, siginfo_t *info, void *ctx_void)
 int main()
 {
 	stack_t stack = {
-		.ss_sp = altstack_data,
+		/* Our sigaltstack scratch space. */
+		.ss_sp = malloc(sizeof(char) * SIGSTKSZ),
 		.ss_size = SIGSTKSZ,
 	};
 	if (sigaltstack(&stack, NULL) != 0)
@@ -233,5 +231,6 @@ int main()
 	set_eflags(get_eflags() & ~X86_EFLAGS_TF);
 #endif
 
+	free(stack.ss_sp);
 	return 0;
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 44/53] platform/x86: dell-smbios-wmi: Avoid false-positive memcpy() warning

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit fb49d9946f96081f9a05d8f305b3f40285afe4a9 ]

In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally writing across neighboring fields.

Since all the size checking has already happened, use input.pointer
(void *) so memcpy() doesn't get confused about how much is being
written.

Avoids this false-positive warning when run-time memcpy() strict
bounds checking is enabled:

memcpy: detected field-spanning write (size 4096) of single field (size 36)
WARNING: CPU: 0 PID: 357 at drivers/platform/x86/dell/dell-smbios-wmi.c:74 run_smbios_call+0x110/0x1e0 [dell_smbios]

Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Mark Gross <mgross@linux.intel.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Cc: "Pali Rohár" <pali@kernel.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "Uwe Kleine-König" <u.kleine-koenig@pengutronix.de>
Cc: Dell.Client.Kernel@dell.com
Cc: platform-driver-x86@vger.kernel.org
Reported-by: Andy Lavr <andy.lavr@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210825160749.3891090-1-keescook@chromium.org
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/platform/x86/dell-smbios-wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c
index c97bd4a45242..32e8c4715d53 100644
--- a/drivers/platform/x86/dell-smbios-wmi.c
+++ b/drivers/platform/x86/dell-smbios-wmi.c
@@ -71,7 +71,7 @@ static int run_smbios_call(struct wmi_device *wdev)
 				obj->integer.value);
 		return -EIO;
 	}
-	memcpy(&priv->buf->std, obj->buffer.pointer, obj->buffer.length);
+	memcpy(input.pointer, obj->buffer.pointer, obj->buffer.length);
 	dev_dbg(&wdev->dev, "result: [%08x,%08x,%08x,%08x]\n",
 		priv->buf->std.output[0], priv->buf->std.output[1],
 		priv->buf->std.output[2], priv->buf->std.output[3]);
-- 
2.30.2

[PATCH AUTOSEL 5.10 45/53] clk: zynqmp: Fix a memory leak

[Sasha Levin]

From: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>

[ Upstream commit e7296d16ef7be11a6001be9bd89906ef55ab2405 ]

Fix a memory leak of mux.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Link: https://lore.kernel.org/r/20210818065929.12835-3-shubhrajyoti.datta@xilinx.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/zynqmp/clk-mux-zynqmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/zynqmp/clk-mux-zynqmp.c b/drivers/clk/zynqmp/clk-mux-zynqmp.c
index 06194149be83..d3b88384b2ff 100644
--- a/drivers/clk/zynqmp/clk-mux-zynqmp.c
+++ b/drivers/clk/zynqmp/clk-mux-zynqmp.c
@@ -130,7 +130,7 @@ struct clk_hw *zynqmp_clk_register_mux(const char *name, u32 clk_id,
 	hw = &mux->hw;
 	ret = clk_hw_register(NULL, hw);
 	if (ret) {
-		kfree(hw);
+		kfree(mux);
 		hw = ERR_PTR(ret);
 	}
 
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.10 45/53] clk: zynqmp: Fix a memory leak

[Sasha Levin]

From: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>

[ Upstream commit e7296d16ef7be11a6001be9bd89906ef55ab2405 ]

Fix a memory leak of mux.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Link: https://lore.kernel.org/r/20210818065929.12835-3-shubhrajyoti.datta@xilinx.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clk/zynqmp/clk-mux-zynqmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/zynqmp/clk-mux-zynqmp.c b/drivers/clk/zynqmp/clk-mux-zynqmp.c
index 06194149be83..d3b88384b2ff 100644
--- a/drivers/clk/zynqmp/clk-mux-zynqmp.c
+++ b/drivers/clk/zynqmp/clk-mux-zynqmp.c
@@ -130,7 +130,7 @@ struct clk_hw *zynqmp_clk_register_mux(const char *name, u32 clk_id,
 	hw = &mux->hw;
 	ret = clk_hw_register(NULL, hw);
 	if (ret) {
-		kfree(hw);
+		kfree(mux);
 		hw = ERR_PTR(ret);
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 46/53] MIPS: ingenic: Unconditionally enable clock of CPU #0

[Sasha Levin]

From: Paul Cercueil <paul@crapouillou.net>

[ Upstream commit 71f8817c28e2e1e5549138e2aef68c2fd784e162 ]

Make sure that the PLL that feeds the CPU won't be stopped while the
kernel is running.

This fixes a problem on JZ4760 (and probably others) where under very
specific conditions, the main PLL would be turned OFF when the kernel
was shutting down, causing the shutdown process to fail.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/mips/generic/board-ingenic.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/arch/mips/generic/board-ingenic.c b/arch/mips/generic/board-ingenic.c
index 0cec0bea13d6..11387a93867b 100644
--- a/arch/mips/generic/board-ingenic.c
+++ b/arch/mips/generic/board-ingenic.c
@@ -7,6 +7,8 @@
  * Copyright (C) 2020 Paul Cercueil <paul@crapouillou.net>
  */
 
+#include <linux/clk.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/pm.h>
@@ -108,10 +110,36 @@ static const struct platform_suspend_ops ingenic_pm_ops __maybe_unused = {
 
 static int __init ingenic_pm_init(void)
 {
+	struct device_node *cpu_node;
+	struct clk *cpu0_clk;
+	int ret;
+
 	if (boot_cpu_type() == CPU_XBURST) {
 		if (IS_ENABLED(CONFIG_PM_SLEEP))
 			suspend_set_ops(&ingenic_pm_ops);
 		_machine_halt = ingenic_halt;
+
+		/*
+		 * Unconditionally enable the clock for the first CPU.
+		 * This makes sure that the PLL that feeds the CPU won't be
+		 * stopped while the kernel is running.
+		 */
+		cpu_node = of_get_cpu_node(0, NULL);
+		if (!cpu_node) {
+			pr_err("Unable to get CPU node\n");
+		} else {
+			cpu0_clk = of_clk_get(cpu_node, 0);
+			if (IS_ERR(cpu0_clk)) {
+				pr_err("Unable to get CPU0 clock\n");
+				return PTR_ERR(cpu0_clk);
+			}
+
+			ret = clk_prepare_enable(cpu0_clk);
+			if (ret) {
+				pr_err("Unable to enable CPU0 clock\n");
+				return ret;
+			}
+		}
 	}
 
 	return 0;
-- 
2.30.2

[PATCH AUTOSEL 5.10 47/53] ext4: if zeroout fails fall back to splitting the extent node

[Sasha Levin]

From: Theodore Ts'o <tytso@mit.edu>

[ Upstream commit 308c57ccf4318236be75dfa251c84713e694457b ]

If the underlying storage device is using thin-provisioning, it's
possible for a zeroout operation to return ENOSPC.

Commit df22291ff0fd ("ext4: Retry block allocation if we have free blocks
left") added logic to retry block allocation since we might get free block
after we commit a transaction. But the ENOSPC from thin-provisioning
will confuse ext4, and lead to an infinite loop.

Since using zeroout instead of splitting the extent node is an
optimization, if it fails, we might as well fall back to splitting the
extent node.

Reported-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ext4/extents.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e00a35530a4e..6af3a36d20be 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3568,7 +3568,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 				split_map.m_len - ee_block);
 			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
-				goto out;
+				goto fallback;
 			split_map.m_len = allocated;
 		}
 		if (split_map.m_lblk - ee_block + split_map.m_len <
@@ -3582,7 +3582,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 						      ext4_ext_pblock(ex));
 				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
-					goto out;
+					goto fallback;
 			}
 
 			split_map.m_len += split_map.m_lblk - ee_block;
@@ -3591,6 +3591,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		}
 	}
 
+fallback:
 	err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag,
 				flags);
 	if (err > 0)
-- 
2.30.2

[PATCH AUTOSEL 5.10 48/53] ext4: Make sure quota files are not grabbed accidentally

[Sasha Levin]

From: Jan Kara <jack@suse.cz>

[ Upstream commit bd2c38cf1726ea913024393a0d11f2e2a3f4c180 ]

If ext4 filesystem is corrupted so that quota files are linked from
directory hirerarchy, bad things can happen. E.g. quota files can get
corrupted or deleted. Make sure we are not grabbing quota file inodes
when we expect normal inodes.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20210812133122.26360-1-jack@suse.cz
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ext4/inode.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 18a5321b5ef3..b90493875174 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4604,6 +4604,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	struct ext4_iloc iloc;
 	struct ext4_inode *raw_inode;
 	struct ext4_inode_info *ei;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	struct inode *inode;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
@@ -4614,9 +4615,12 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	projid_t i_projid;
 
 	if ((!(flags & EXT4_IGET_SPECIAL) &&
-	     (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)) ||
+	     ((ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) ||
+	      ino == le32_to_cpu(es->s_usr_quota_inum) ||
+	      ino == le32_to_cpu(es->s_grp_quota_inum) ||
+	      ino == le32_to_cpu(es->s_prj_quota_inum))) ||
 	    (ino < EXT4_ROOT_INO) ||
-	    (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) {
+	    (ino > le32_to_cpu(es->s_inodes_count))) {
 		if (flags & EXT4_IGET_HANDLE)
 			return ERR_PTR(-ESTALE);
 		__ext4_error(sb, function, line, EFSCORRUPTED, 0,
-- 
2.30.2

[PATCH AUTOSEL 5.10 49/53] xen: remove stray preempt_disable() from PV AP startup code

[Sasha Levin]

From: Juergen Gross <jgross@suse.com>

[ Upstream commit 58e636039b512697554b579c2bb23774061877f5 ]

In cpu_bringup() there is a call of preempt_disable() without a paired
preempt_enable(). This is not needed as interrupts are off initially.
Additionally this will result in early boot messages like:

BUG: scheduling while atomic: swapper/1/0/0x00000002

Signed-off-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20210825113158.11716-1-jgross@suse.com
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/xen/smp_pv.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index c2ac319f11a4..96afadf9878e 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -64,7 +64,6 @@ static void cpu_bringup(void)
 	cr4_init();
 	cpu_init();
 	touch_softlockup_watchdog();
-	preempt_disable();
 
 	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
 	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 50/53] checkkconfigsymbols.py: Fix the '--ignore' option

[Sasha Levin]

From: Ariel Marcovitch <arielmarcovitch@gmail.com>

[ Upstream commit 1439ebd2ce77242400518d4e6a1e85bebcd8084f ]

It seems like the implementation of the --ignore option is broken.

In check_symbols_helper, when going through the list of files, a file is
added to the list of source files to check if it matches the ignore
pattern. Instead, as stated in the comment below this condition, the
file should be added if it doesn't match the pattern.

This means that when providing an ignore pattern, the only files that
will be checked will be the ones we want the ignore, in addition to the
Kconfig files that don't match the pattern (the check in
parse_kconfig_files is done right)

Signed-off-by: Ariel Marcovitch <arielmarcovitch@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 scripts/checkkconfigsymbols.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/checkkconfigsymbols.py b/scripts/checkkconfigsymbols.py
index 1548f9ce4682..b9b0f15e5880 100755
--- a/scripts/checkkconfigsymbols.py
+++ b/scripts/checkkconfigsymbols.py
@@ -329,7 +329,7 @@ def check_symbols_helper(pool, ignore):
         if REGEX_FILE_KCONFIG.match(gitfile):
             kconfig_files.append(gitfile)
         else:
-            if ignore and not re.match(ignore, gitfile):
+            if ignore and re.match(ignore, gitfile):
                 continue
             # add source files that do not match the ignore pattern
             source_files.append(gitfile)
-- 
2.30.2

[Ocfs2-devel] [PATCH AUTOSEL 5.10 51/53] ocfs2: quota_local: fix possible uninitialized-variable access in ocfs2_local_read_info()

[Sasha Levin]

From: Tuo Li <islituo@gmail.com>

[ Upstream commit 6c85c2c728193d19d6a908ae9fb312d0325e65ca ]

A memory block is allocated through kmalloc(), and its return value is
assigned to the pointer oinfo. However, oinfo->dqi_gqinode is not
initialized but it is accessed in:
  iput(oinfo->dqi_gqinode);

To fix this possible uninitialized-variable access, assign NULL to
oinfo->dqi_gqinode, and add ocfs2_qinfo_lock_res_init() behind the
assignment in ocfs2_local_read_info().  Remove ocfs2_qinfo_lock_res_init()
in ocfs2_global_read_info().

Link: https://lkml.kernel.org/r/20210804031832.57154-1-islituo@gmail.com
Signed-off-by: Tuo Li <islituo@gmail.com>
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ocfs2/quota_global.c | 1 -
 fs/ocfs2/quota_local.c  | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index eda83487c9ec..f033de733adb 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -357,7 +357,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type)
 	}
 	oinfo->dqi_gi.dqi_sb = sb;
 	oinfo->dqi_gi.dqi_type = type;
-	ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo);
 	oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk);
 	oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops;
 	oinfo->dqi_gqi_bh = NULL;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index b1a8b046f4c2..0e4b16d4c037 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -702,6 +702,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	info->dqi_priv = oinfo;
 	oinfo->dqi_type = type;
 	INIT_LIST_HEAD(&oinfo->dqi_chunk);
+	oinfo->dqi_gqinode = NULL;
+	ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo);
 	oinfo->dqi_rec = NULL;
 	oinfo->dqi_lqi_bh = NULL;
 	oinfo->dqi_libh = NULL;
-- 
2.30.2


_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel@oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel

[PATCH AUTOSEL 5.10 51/53] ocfs2: quota_local: fix possible uninitialized-variable access in ocfs2_local_read_info()

[Sasha Levin]

From: Tuo Li <islituo@gmail.com>

[ Upstream commit 6c85c2c728193d19d6a908ae9fb312d0325e65ca ]

A memory block is allocated through kmalloc(), and its return value is
assigned to the pointer oinfo. However, oinfo->dqi_gqinode is not
initialized but it is accessed in:
  iput(oinfo->dqi_gqinode);

To fix this possible uninitialized-variable access, assign NULL to
oinfo->dqi_gqinode, and add ocfs2_qinfo_lock_res_init() behind the
assignment in ocfs2_local_read_info().  Remove ocfs2_qinfo_lock_res_init()
in ocfs2_global_read_info().

Link: https://lkml.kernel.org/r/20210804031832.57154-1-islituo@gmail.com
Signed-off-by: Tuo Li <islituo@gmail.com>
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ocfs2/quota_global.c | 1 -
 fs/ocfs2/quota_local.c  | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index eda83487c9ec..f033de733adb 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -357,7 +357,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type)
 	}
 	oinfo->dqi_gi.dqi_sb = sb;
 	oinfo->dqi_gi.dqi_type = type;
-	ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo);
 	oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk);
 	oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops;
 	oinfo->dqi_gqi_bh = NULL;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index b1a8b046f4c2..0e4b16d4c037 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -702,6 +702,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	info->dqi_priv = oinfo;
 	oinfo->dqi_type = type;
 	INIT_LIST_HEAD(&oinfo->dqi_chunk);
+	oinfo->dqi_gqinode = NULL;
+	ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo);
 	oinfo->dqi_rec = NULL;
 	oinfo->dqi_lqi_bh = NULL;
 	oinfo->dqi_libh = NULL;
-- 
2.30.2

[Ocfs2-devel] [PATCH AUTOSEL 5.10 52/53] ocfs2: ocfs2_downconvert_lock failure results in deadlock

[Sasha Levin]

From: Gang He <ghe@suse.com>

[ Upstream commit 9673e0050c39b0534d0e2ca431223f52089f4959 ]

Usually, ocfs2_downconvert_lock() function always downconverts dlm lock to
the expected level for satisfy dlm bast requests from the other nodes.

But there is a rare situation.  When dlm lock conversion is being
canceled, ocfs2_downconvert_lock() function will return -EBUSY.  You need
to be aware that ocfs2_cancel_convert() function is asynchronous in fsdlm
implementation.

If we does not requeue this lockres entry, ocfs2 downconvert thread no
longer handles this dlm lock bast request.  Then, the other nodes will not
get the dlm lock again, the current node's process will be blocked when
acquire this dlm lock again.

Link: https://lkml.kernel.org/r/20210830044621.12544-1-ghe@suse.com
Signed-off-by: Gang He <ghe@suse.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ocfs2/dlmglue.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8e3a369086db..01cf5211b5c8 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -18,6 +18,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/time.h>
+#include <linux/delay.h>
 #include <linux/quotaops.h>
 #include <linux/sched/signal.h>
 
@@ -3906,6 +3907,17 @@ static int ocfs2_unblock_lock(struct ocfs2_super *osb,
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
 	ret = ocfs2_downconvert_lock(osb, lockres, new_level, set_lvb,
 				     gen);
+	/* The dlm lock convert is being cancelled in background,
+	 * ocfs2_cancel_convert() is asynchronous in fs/dlm,
+	 * requeue it, try again later.
+	 */
+	if (ret == -EBUSY) {
+		ctl->requeue = 1;
+		mlog(ML_BASTS, "lockres %s, ReQ: Downconvert busy\n",
+		     lockres->l_name);
+		ret = 0;
+		msleep(20);
+	}
 
 leave:
 	if (ret)
-- 
2.30.2


_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel@oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel

[PATCH AUTOSEL 5.10 52/53] ocfs2: ocfs2_downconvert_lock failure results in deadlock

[Sasha Levin]

From: Gang He <ghe@suse.com>

[ Upstream commit 9673e0050c39b0534d0e2ca431223f52089f4959 ]

Usually, ocfs2_downconvert_lock() function always downconverts dlm lock to
the expected level for satisfy dlm bast requests from the other nodes.

But there is a rare situation.  When dlm lock conversion is being
canceled, ocfs2_downconvert_lock() function will return -EBUSY.  You need
to be aware that ocfs2_cancel_convert() function is asynchronous in fsdlm
implementation.

If we does not requeue this lockres entry, ocfs2 downconvert thread no
longer handles this dlm lock bast request.  Then, the other nodes will not
get the dlm lock again, the current node's process will be blocked when
acquire this dlm lock again.

Link: https://lkml.kernel.org/r/20210830044621.12544-1-ghe@suse.com
Signed-off-by: Gang He <ghe@suse.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ocfs2/dlmglue.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8e3a369086db..01cf5211b5c8 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -18,6 +18,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/time.h>
+#include <linux/delay.h>
 #include <linux/quotaops.h>
 #include <linux/sched/signal.h>
 
@@ -3906,6 +3907,17 @@ static int ocfs2_unblock_lock(struct ocfs2_super *osb,
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
 	ret = ocfs2_downconvert_lock(osb, lockres, new_level, set_lvb,
 				     gen);
+	/* The dlm lock convert is being cancelled in background,
+	 * ocfs2_cancel_convert() is asynchronous in fs/dlm,
+	 * requeue it, try again later.
+	 */
+	if (ret == -EBUSY) {
+		ctl->requeue = 1;
+		mlog(ML_BASTS, "lockres %s, ReQ: Downconvert busy\n",
+		     lockres->l_name);
+		ret = 0;
+		msleep(20);
+	}
 
 leave:
 	if (ret)
-- 
2.30.2

[PATCH AUTOSEL 5.10 53/53] kasan: test: avoid corrupting memory in kasan_rcu_uaf

[Sasha Levin]

From: Andrey Konovalov <andreyknvl@gmail.com>

[ Upstream commit f16de0bcdb55bf18e2533ca625f3e4b4952f254c ]

kasan_rcu_uaf() writes to freed memory via kasan_rcu_reclaim(), which is
only safe with the GENERIC mode (as it uses quarantine).  For other modes,
this test corrupts kernel memory, which might result in a crash.

Turn the write into a read.

Link: https://lkml.kernel.org/r/b6f2c3bf712d2457c783fa59498225b66a634f62.1628779805.git.andreyknvl@gmail.com
Signed-off-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 lib/test_kasan_module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/test_kasan_module.c b/lib/test_kasan_module.c
index 2d68db6ae67b..1c6e06136f78 100644
--- a/lib/test_kasan_module.c
+++ b/lib/test_kasan_module.c
@@ -73,7 +73,7 @@ static noinline void __init kasan_rcu_reclaim(struct rcu_head *rp)
 						struct kasan_rcu_info, rcu);
 
 	kfree(fp);
-	fp->i = 1;
+	((volatile struct kasan_rcu_info *)fp)->i;
 }
 
 static noinline void __init kasan_rcu_uaf(void)
-- 
2.30.2